SEARCH · PubMed Health

Results for “generative artificial intelligence”

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 271 records · Page 15Linked to original sources

PubMed1997

INKBLOT: a neurological diagnostic decision support system integrating causal and anatomical knowledge.

As an initial step in the diagnostic process, human neurologists often use anatomical localization to constrain the set of diagnostic hypotheses deserving further consideration. We describe an automated system, INKBLOT-1, which uses anatomical localization in much the same way as human neurologists. Given a set of manifestations, INKBLOT-1 generates a set of hypothetical localizations relative to a coordinate system of nested cubes and then uses these localization(s) to explain the manifestations. We trace the reasoning mechanism utilized by INKBLOT-1 for a particular set of symptoms and show how INKBLOT-1 is able to generate novel hypotheses that explain the observed manifestations. In doing this, INKBLOT-1 demonstrates capabilities not demonstrated by previously described systems.

Artificial Intelligence↗

PubMed2005

Enhanced FMAM based on empirical kernel map.

The existing morphological auto-associative memory models based on the morphological operations, typically including morphological auto-associative memories (auto-MAM) proposed by Ritter et al. and our fuzzy morphological auto-associative memories (auto-FMAM), have many attractive advantages such as unlimited storage capacity, one-shot recall speed and good noise-tolerance to single erosive or dilative noise. However, they suffer from the extreme vulnerability to noise of mixing erosion and dilation, resulting in great degradation on recall performance. To overcome this shortcoming, we focus on FMAM and propose an enhanced FMAM (EFMAM) based on the empirical kernel map. Although it is simple, EFMAM can significantly improve the auto-FMAM with respect to the recognition accuracy under hybrid-noise and computational effort. Experiments conducted on the thumbnail-sized faces (28 x 23 and 14 x 11) scaled from the ORL database show the average accuracies of 92%, 90%, and 88% with 40 classes under 10%, 20%, and 30% randomly generated hybrid-noises, respectively, which are far higher than the auto-FMAM (67%, 46%, 31%) under the same noise levels.

Algorithms↗

PubMed2005

Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities.

Many vision tasks can be formulated as graph partition problems that minimize energy functions. For such problems, the Gibbs sampler provides a general solution but is very slow, while other methods, such as Ncut and graph cuts are computationally effective but only work for specific energy forms and are not generally applicable. In this paper, we present a new inference algorithm that generalizes the Swendsen-Wang method to arbitrary probabilities defined on graph partitions. We begin by computing graph edge weights, based on local image features. Then, the algorithm iterates two steps. 1) Graph clustering: It forms connected components by cutting the edges probabilistically based on their weights. 2) Graph relabeling: It selects one connected component and flips probabilistically, the coloring of all vertices in the component simultaneously. Thus, it realizes the split, merge, and regrouping of a "chunk" of the graph, in contrast to Gibbs sampler that flips a single vertex. We prove that this algorithm simulates ergodic and reversible Markov chain jumps in the space of graph partitions and is applicable to arbitrary posterior probabilities or energy functions defined on graphs. We demonstrate the algorithm on two typical problems in computer vision--image segmentation and stereo vision. Experimentally, we show that it is 100-400 times faster in CPU time than the classical Gibbs sampler and 20-40 times faster then the DDMCMC segmentation algorithm. For stereo, we compare performance with graph cuts and belief propagation. We also show that our algorithm can automatically infer generative models and obtain satisfactory results (better than the graphic cuts or belief propagation) in the same amount of time.

Algorithms↗

PubMed2006

Planar-shape prototype generation using a tree-based random greedy algorithm.

A prototype is representative of a set of similar objects. This paper proposes an approach that formulates the problem of prototype generation as finding the mean from a given set of objects, where the prototype solution must satisfy certain constraints. These constraints describe the important perceptual features of the sample shapes that the proposed prototype must retain. The contour prototype generated from a set of planar objects was used as an example of the approach, and the corners were used as the perceptual features to be preserved in the proposed prototype shape. However, finding a prototype solution for more than two contours is computationally intractable. A tree-based approach is therefore proposed in which an efficient greedy random algorithm is used to obtain a good approximation of the proposed prototype and analyze the expected complexity of the algorithm. The proposed prototype-generation process for hand-drawn patterns is described and discussed in this paper.

Algorithms↗

PubMed2000

Learning chaotic attractors by neural networks.

An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time series. During training, the algorithm learns to short-term predict the time series. At the same time a criterion, developed by Diks, van Zwet, Takens, and de Goede (1996) is monitored that tests the hypothesis that the reconstructed attractors of model-generated and measured data are the same. Training is stopped when the prediction error is low and the model passes this test. Two other features of the algorithm are (1) the way the state of the system, consisting of delays from the time series, has its dimension reduced by weighted principal component analysis data reduction, and (2) the user-adjustable prediction horizon obtained by "error propagation"-partially propagating prediction errors to the next time step. The algorithm is first applied to data from an experimental-driven chaotic pendulum, of which two of the three state variables are known. This is a comprehensive example that shows how well the Diks test can distinguish between slightly different attractors. Second, the algorithm is applied to the same problem, but now one of the two known state variables is ignored. Finally, we present a model for the laser data from the Santa Fe time-series competition (set A). It is the first model for these data that is not only useful for short-term predictions but also generates time series with similar chaotic characteristics as the measured data.

Algorithms↗

PubMed2001

Alternative voice after laryngectomy using a sound-producing voice prosthesis.

OBJECTIVE: To improve the voice quality of female laryngectomees and/or laryngectomees with a hypotonic pharyngoesophageal (PE) segment by means of a pneumatic artificial source of voice incorporated in a regular tracheoesophageal (TE) shunt valve. STUDY DESIGN: Experimental, randomized, crossover trial. METHODS: The new sound source consists of a single silicone lip, which performs an oscillatory movement driven by expired pulmonary air flowing along the outward-striking lip through the TE shunt valve. A prototype of this pneumatic sound source is evaluated in vitro and in six laryngectomees. In vivo evaluation includes speech rate, maximal phonation time, perceptual voice evaluation of read-aloud prose by an expert listener, speech intelligibility measurements with 12 listeners, and self-assessment by the patients. Moreover, extensive acoustical and aerodynamic in vivo registrations are performed using a newly developed data acquisition system. RESULTS: The current prototype seems beneficial in female laryngectomees with a hypotonic PE segment only. For them the sound-producing voice prosthesis improves voice quality and increases the average pitch of voice, without decreasing intelligibility or necessitating other pressure and airflow rates than regular TE shunt speech. Pitch regulation of this prosthetic voice is possible, yet limited. CONCLUSIONS: The mechanism is feasible and does not result in unacceptable airflow resistance. For this new mechanism of alaryngeal voice to become an established technique for postlaryngectomy voice restoration, a voice suitably pitched for male laryngectomees has to be generated and a large part of the melodic and dynamic range of the sound source has to be attainable within physiological airflow rates.

Aged↗

PubMed2005

Automated nomenclature of bronchial branches extracted from CT images and its application to biopsy path planning in virtual bronchoscopy.

We propose a novel anatomical labeling algorithm for bronchial branches extracted from CT images. This method utilizes multiple branching models for anatomical labeling. In the actual labeling process, the method selects the best candidate models at each branching point. Also a special labeling procedure is proposed for the right upper lobe. As an application of the automated nomenclature of bronchial branches, we utilized anatomical labeling results for assisting biopsy planning. When a user inputs a target point around suspicious regions on the display of a virtual bronchoscopy (VB) system, the path to the desired position is displayed as a sequence of anatomical names of branches. We applied the proposed method to 25 cases of CT images. The labeling accuracy was about 90%. Also the paths to desired positions were generated by using anatomical names in VB.

Algorithms↗

PubMed2006

Identifying the interacting positions of a protein using Boolean learning and support vector machines.

It is known that in the three-dimensional structure of a protein, certain amino acids can interact with each other in order to provide structural integrity or aid in its catalytic function. If these positions are mutated the loss of this interaction usually leads to a non-functional protein. Directed evolution experiments, which probe the sequence space of a protein through mutations in search for an improved variant, frequently result in such inactive sequences. In this work, we address the use of machine learning algorithms, Boolean learning and support vector machines (SVMs), to find such pairs of amino acid positions. The recombination method of imparting mutations was simulated to create in silico sequences that were used as training data for the algorithms. The two algorithms were combined together to develop an approach that weighs the structural risk as well as the empirical risk to solve the problem. This strategy was adapted to a multi-round framework of experiments where the data generated in the present round is used to design experiments for the next round to improve the generated library, as well as the estimation of the interacting positions. It is observed that this strategy can greatly improve the number of functional variants that are generated as well as the average number of mutations that can be made in the library.

Algorithms↗

PubMed2005

Generalized hamming networks and applications.

In this paper the classical Hamming network is generalized in various ways. First, for the Hamming maxnet, a generalized model is proposed, which covers under its umbrella most of the existing versions of the Hamming Maxnet. The network dynamics are time varying while the commonly used ramp function may be replaced by a much more general non-linear function. Also, the weight parameters of the network are time varying. A detailed convergence analysis is provided. A bound on the number of iterations required for convergence is derived and its distribution functions are given for the cases where the initial values of the nodes of the Hamming maxnet stem from the uniform and the peak distributions. Stabilization mechanisms aiming to prevent the node(s) with the maximum initial value diverging to infinity or decaying to zero are described. Simulations demonstrate the advantages of the proposed extension. Also, a rough comparison between the proposed generalized scheme as well as the original Hamming maxnet and its variants is carried out in terms of the time required for convergence, in hardware implementations. Finally, the other two parts of the Hamming network, namely the competitors generating module and the decoding module, are briefly considered in the framework of various applications such as classification/clustering, vector quantization and function optimization.

Algorithms↗

PubMedDate not supplied

Comparison of knowledge-based and distance geometry approaches for generation of molecular conformations.

A knowledge-based approach for generating conformations of molecules has been developed. The method described here provides a good sampling of the molecule's conformational space by restricting the generated conformations to those consistent with the reference database. The present approach, internally named et for enumerate torsions, differs from previous database-mining approaches by employing a library of much larger substructures while treating open chains, rings, and combinations of chains and rings in the same manner. In addition to knowledge in the form of observed torsion angles, some knowledge from the medicinal chemist is captured in the form of which substructures are identified. The knowledge-based approach is compared to Blaney et al.'s distance geometry (DG) algorithm for sampling the conformational space of molecules. The structures of 113 protein-bound molecules, determined by X-ray crystallography, were used to compare the methods. The present knowledge-based approach (i) generates conformations closer to the experimentally determined conformation, (ii) generates them sooner, and (iii) is significantly faster than the DG method.

Algorithms↗

PubMed2005

Artificial neural networks for document analysis and recognition.

Artificial neural networks have been extensively applied to document analysis and recognition. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document processing tasks, like preprocessing, layout analysis, character segmentation, word recognition, and signature verification, have been effectively faced with very promising results. This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied. Similarities and differences between approaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts the most promising research guidelines in the field. In particular, a second generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.

Algorithms↗

PubMed1989

Creation of realistic appearing simulated patient cases using the INTERNIST-1/QMR knowledge base and interrelationship properties of manifestations.

The Internist-1/Quick Medical Reference (QMR) knowledge base (KB) describes the clinical manifestations of some 600 diseases in the domain of internal medicine. This KB, while not representing deep causal modelling of disease processes, is nonetheless effective in providing medical diagnostic assistance through the QMR medical decision support system. One potential application of this extensive KB is the generation of simulated patient cases for use in educating health professionals. However, the "flat" KB is not adequate for this because the clinical manifestations used in the disease descriptions are not mutually independent. While it is theoretically possible to construct disease descriptions which embody pathophysiologic mechanisms of disease causality, it is not practical from the standpoint of resource utilization. Short of constructing a causal knowledge base, the authors herein describe the generation of realistic appearing simulated patient case data using existing information in the knowledge base. This existing information in the KB is in the form of properties which represent a shallow form of interrelationships of the manifestations. The authors conclude that this ability to generate simulated cases represents another view in which to look at an extensive knowledge base, as well as having application to constructing intelligent tutoring systems for health professionals in training.

Artificial Intelligence↗

PubMed2002

(Physio)logical circuits: the intellectual origins of the McCulloch-Pitts neural networks.

This article examines the intellectual and institutional factors that contributed to the collaboration of neuropsychiatrist Warren McCulloch and mathematician Walter Pitts on the logic of neural networks, which culminated in their 1943 publication, "A Logical Calculus of the Ideas Immanent in Nervous Activity." Historians and scientists alike often refer to the McCulloch-Pitts paper as a landmark event in the history of cybernetics, and fundamental to the development of cognitive science and artificial intelligence. This article seeks to bring some historical context to the McCulloch-Pitts collaboration itself, namely, their intellectual and scientific orientations and backgrounds, the key concepts that contributed to their paper, and the institutional context in which their collaboration was made. Although they were almost a generation apart and had dissimilar scientific backgrounds, McCulloch and Pitts had similar intellectual concerns, simultaneously motivated by issues in philosophy, neurology, and mathematics. This article demonstrates how these issues converged and found resonance in their model of neural networks. By examining the intellectual backgrounds of McCulloch and Pitts as individuals, it will be shown that besides being an important event in the history of cybernetics proper, the McCulloch-Pitts collaboration was an important result of early twentieth-century efforts to apply mathematics to neurological phenomena.

Biology↗

PubMedDate not supplied

Ovarian cancer diagnosis by hippocampus and neocortex-inspired learning memory structures.

Early detection and accurate staging of ovarian cancer are the keys to improving survival rate. However, at present there is no single diagnosis modality that is sufficiently sensitive. DNA microarray analysis is an emerging technique that has potential for ameliorating the hardship in early detection and staging of ovarian disease. However, microarray data is ultra-huge and difficult to analyze. Hence, computational intelligence methods are often utilized to assist in the diagnosis and analysis process. Fuzzy Neural Networks (FNN) are more suitable for this task as FNN provides not only the accuracy, but also the interpretability of its reasoning process. Hippocampus-inspired Complementary Learning FNN (CLFNN) is able to rapidly derive fuzzy sets and formulate fuzzy rules. CLFNN uses positive and negative learning, and hence it reduces the effect of the curse of dimensionality and is capable of modeling the dynamics of the problem space with relatively good classification performance. One of its successors, a hybrid of complementary hippocampal learning and associative neocortical learning called Pseudo Associative Complementary Learning (PACL), is a structure that seeks to functionally model the memory consolidation process. Both PACL and CLFNN have human-like reasoning that allows physicians to examine their computation using familiar terms. They can construct intuitive fuzzy rules autonomously to justify their reasoning, which is important to generate trust among the users. Hence, CLFNN and PACL are applied as a diagnostic decision support system in ovarian cancer diagnosis. The experimental results are encouraging.

Algorithms↗

PubMed2002

A methodology for incorporating web technologies into a computer-based patient record, with contributions from cognitive science.

Cognitive science is a rich source of insight for creative use of new Web technologies by medical informatics workers. I outline a project to Web-enable an existing computer-based patient record (CPR) in the context of ideas from philosophy, linguistics, artificial intelligence, and cognitive psychology. Web prototypes play an important role (a) because Web technology lends itself to rapid prototype development, and (b) because prototypes help team members bridge among disparate medical, computing, and business ontologies. Six Web-enabled CPR prototypes were created and ranked. User scenarios were generated using a user communication matrix. Resulting prototypes were compared according to the degree to which they satisfied medical, computing, and business constraints. In a different organization, or at different time, candidate prototypes and their ranking might have been different. However, prototype generation and comparison are fundamentally influenced by factors usefully understood in a cognitive science framework.

Cognitive Science↗

PubMed2001

A methodology for web-enabling a computer-based patient record with contributions from cognitive science.

Cognitive Science↗

PubMed2006

3-D reconstruction of tissue components for atherosclerotic human arteries using ex vivo high-resolution MRI.

Automatic computer-based methods are well suited for the image analysis of the different components in atherosclerotic plaques. Although several groups work on such analysis some of the methods used are oversimplified and require improvements when used within a computational framework for predicting meaningful stress and strain distributions in the heterogeneous arterial wall under various loading conditions. Based on high-resolution magnetic resonance imaging of excised atherosclerotic human arteries and a series of two-dimensional (2-D) contours we present a segmentation tool that permits a three-dimensional (3-D) reconstruction of the most important tissue components of atherosclerotic arteries. The underlying principle of the proposed approach is a model-based snake algorithm for identifying 2-D contours, which uses information about the plaque composition and geometric data of the tissue layers. Validation of the computer-generated tissue boundaries is performed with 100 MR images, which are compared with the results of a manual segmentation performed by four experts. Based on the Hausdorff distance and the average distance for computer-to-expert differences and the interexpert differences for the outer boundary of the adventitia, the adventitia-media, media-intima, intima-lumen and calcification boundaries are less than 1 pixel (0.234 mm). The percentage statistic shows similar results to the modified Williams index in terms of accuracy. Except for the identification of lipid-rich regions the proposed algorithm is automatic. The nonuniform rational B-spline-based computer-generated 3-D models of the individual tissue components provide a basis for clinical and computational analysis.

Algorithms↗

PubMedDate not supplied

A method to generate soft shadows using a layered depth image and warping.

We present an image-based method for propagating area light illumination through a Layered Depth Image (LDI) to generate soft shadows from opaque and nonrefractive transparent objects. In our approach, using the depth peeling technique, we render an LDI from a reference light sample on a planar light source. Light illumination of all pixels in an LDI is then determined for all the other sample points via warping, an image-based rendering technique, which approximates ray tracing in our method. We use an image-warping equation and McMillan's warp ordering algorithm to find the intersections between rays and polygons and to find the order of intersections. Experiments for opaque and nonrefractive transparent objects are presented. Results indicate our approach generates soft shadows fast and effectively. Advantages and disadvantages of the proposed method are also discussed.

Algorithms↗