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 559 records · Page 31Linked to original sources

PubMed2005

Acquiring linear subspaces for face recognition under variable lighting.

Previous work has demonstrated that the image variation of many objects (human faces in particular) under variable lighting can be effectively modeled by low-dimensional linear spaces, even when there are multiple light sources and shadowing. Basis images spanning this space are usually obtained in one of three ways: A large set of images of the object under different lighting conditions is acquired, and principal component analysis (PCA) is used to estimate a subspace. Alternatively, synthetic images are rendered from a 3D model (perhaps reconstructed from images) under point sources and, again, PCA is used to estimate a subspace. Finally, images rendered from a 3D model under diffuse lighting based on spherical harmonics are directly used as basis images. In this paper, we show how to arrange physical lighting so that the acquired images of each object can be directly used as the basis vectors of a low-dimensional linear space and that this subspace is close to those acquired by the other methods. More specifically, there exist configurations of k point light source directions, with k typically ranging from 5 to 9, such that, by taking k images of an object under these single sources, the resulting subspace is an effective representation for recognition under a wide range of lighting conditions. Since the subspace is generated directly from real images, potentially complex and/or brittle intermediate steps such as 3D reconstruction can be completely avoided; nor is it necessary to acquire large numbers of training images or to physically construct complex diffuse (harmonic) light fields. We validate the use of subspaces constructed in this fashion within the context of face recognition.

Algorithms↗

PubMed2005

Three-dimensional sensor-based face recognition.

We describe a face recognition system based on two different three-dimensional (3D) sensors. We use 3D sensors to overcome the pose-variation problems that cannot be effectively solved in two-dimensional images. We acquire input data based on a structured-light system and compare it with 3D faces that are obtained from a 3D laser scanner. Owing to differences in structure between the input data and the 3D faces, we can generate the range images of the probe and stored images. For estimating the head pose of input data, we propose a novel error-compensated singular-value decomposition that geometrically estimates the rotation angle. Face recognition rates obtained with principal component analysis on various range images of 35 people in different poses show promising results.

Algorithms↗

PubMed2004

Intrusion detection using rough set classification.

Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learning algorithm, is used to rank the features extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. RSC performs feature ranking before generating rules, and converts the feature ranking to minimal hitting set problem addressed by using genetic algorithm (GA). This is done in classical approaches using Support Vector Machine (SVM) by executing many iterations, each of which removes one useless feature. Compared with those methods, our method can avoid many iterations. In addition, a hybrid genetic algorithm is proposed to increase the convergence speed and decrease the training time of RSC. The models generated by RSC take the form of "IF-THEN" rules, which have the advantage of explication. Tests and comparison of RSC with SVM on DARPA benchmark data showed that for Probe and DoS attacks both RSC and SVM yielded highly accurate results (greater than 99% accuracy on testing set).

Algorithms↗

PubMed2026

Oncotype DX: Clinical Utility, Evidence, and Future Trends in Personalized Breast Cancer Management.

The Oncotype DX assay has revolutionized the management of early-stage, hormone receptor-positive, HER2-negative breast cancer. Developed in 2004, it quantifies 21 genes to generate a recurrence score that predicts distant recurrence risk and guides adjuvant chemotherapy. Multiple studies have validated its reliability and clinical utility in enabling more precise risk stratification and individualized treatment planning, thereby minimizing unnecessary chemotherapy exposure and improving patient outcomes. Leading oncology organizations such as the American Society of Clinical Oncology and National Comprehensive Cancer Network have incorporated it into their clinical guidelines. Beyond its well-established role in adjuvant chemotherapy decision-making, Oncotype DX is increasingly being investigated in broader clinical contexts, including lymph node-positive breast cancer, neoadjuvant therapy, radiotherapy, and ductal carcinoma in situ. Ongoing research and technological advancements, such as artificial intelligence-based predictive models and novel biomarker identification, hold significant promise for further enhancing its predictive accuracy and expanding its applications. This review synthesizes current evidence supporting the clinical utility of Oncotype DX, discusses evolving applications, and highlights future directions for integrating this genomic tool into precision oncology practice.

Humans↗

PubMed2026

Next-generation brain proteomics: Integrating single-cell, spatial, and multi-omics for clinical biomarker discovery.

The mammalian brain's functional complexity arises from the sophisticated architecture of neurons and glia. This network is essentially defined by its dynamic proteome, which reveals the functional execution underlying neural computation and disease. This review integrates the technological leap in neuroproteomics. It has moved beyond bulk tissue proteome cataloguing to high-sensitivity single-cell and spatial resolution. We detail how next-generation platforms, such as TIMS-PASEF and Orbitrap-Astral, have enabled deeper and faster phenotypic profiling of limited brain samples. However, the proteome coverage remains constrained by dynamic range, sample loss, ionisation bias and incomplete detection of low-abundance regulatory proteins. We further examine how such studies have revealed the proteomic remodelling that drives lineage specification and synaptic plasticity by linking temporal protein expression waves to biological function. Crucially, we delineate the clinical translational trajectory, illustrating how aberrant signatures are verified in cerebrospinal fluid (CSF) and validated in plasma to support precision medicine. Finally, we argue for the necessity of "fused" multi-omics integration and Artificial Intelligence (AI) to decode the non-linear molecular logic of brain pathology.

Humans↗

PubMed1996

A virtual reality interface to an intelligent dental care system.

The design and fabrication of teeth restorations in dentistry rely increasingly on CAD/CAM techniques. We present an approach for interactive design of the occlusal surface of teeth based on simulation of jaw articulation and computer-aided diagnosis of occlusal disorders. To bridge the cognitive gap between the dentist and the computer system, we propose a virtual reality user interface, which applies the metaphors of tools and techniques known in dentistry. This makes the restoration design more intuitive for dentists. The system uses Virtual Reality Modeling Language (VRML) and HTML standards to generate a treatment report and exchange data in an electronic form. The simulation of jaw articulation requires fast calculation of multi-point contacts and detection of collisions between surfaces of teeth and restorations. We have developed a distance maps technique which exhibits realtime performance for objects with complex geometry and is suitable for other virtual reality systems dealing with complex contacts. The characteristics of contacts between teeth acquired during lower jaw motion are compactly represented as accumulated distance maps. These maps are then used for automatic removal of interferences between the restorations and the opponent teeth, and provide the dentist with information for further manual adjustments of the occlusal surfaces.

Artificial Intelligence↗

PubMed2002

Combining biometric and symbolic models for customized, automated prosthesis design.

In a previous paper [Artif. Intell. Med. 5 (1993) 431] we described RaPiD, a knowledge-based system for designing dental prostheses. The present paper discusses how RaPiD has been extended using techniques from computer vision and logic grammars. The first employs point distribution and active shape models (ASMs) to determine dentition from images of casts of patient's jaws. This enables a design to be customized to, and visualised against, an image of a patient's dentition. The second is based on the notion of a path grammar, a form of logic grammar, to generate a path linking an ordered sequence of subcomponents. The shape of an important and complex prosthesis component can be automatically seeded in this fashion. Combining these models now substantially automates the design process, beginning with a photograph of a dental cast and ending with an annotated and validated design diagram ready to guide manufacture.

Anthropometry↗

PubMed2005

Evaluation of an artificial intelligence program for estimating occupational exposures.

Estimation and Assessment of Substance Exposure (EASE) is an artificial intelligence program developed by UK's Health and Safety Executive to assess exposure. EASE computes estimated airborne concentrations based on a substance's vapor pressure and the types of controls in the work area. Though EASE is intended only to make broad predictions of exposure from occupational environments, some occupational hygienists might attempt to use EASE for individual exposure characterizations. This study investigated whether EASE would accurately predict actual sampling results from a chemical manufacturing process. Personal breathing zone time-weighted average (TWA) monitoring data for two volatile organic chemicals--a common solvent (toluene) and a specialty monomer (chloroprene)--present in this manufacturing process were compared to EASE-generated estimates. EASE-estimated concentrations for specific tasks were weighted by task durations reported in the monitoring record to yield TWA estimates from EASE that could be directly compared to the measured TWA data. Two hundred and six chloroprene and toluene full-shift personal samples were selected from eight areas of this manufacturing process. The Spearman correlation between EASE TWA estimates and measured TWA values was 0.55 for chloroprene and 0.44 for toluene, indicating moderate predictive values for both compounds. For toluene, the interquartile range of EASE estimates at least partially overlapped the interquartile range of the measured data distributions in all process areas. The interquartile range of EASE estimates for chloroprene fell above the interquartile range of the measured data distributions in one process area, partially overlapped the third quartile of the measured data in five process areas and fell within the interquartile range in two process areas. EASE is not a substitute for actual exposure monitoring. However, EASE can be used in conditions that cannot otherwise be sampled and in preliminary exposure assessment if it is recognized that the actual interquartile range could be much wider and/or offset by a factor of 10 or more.

Air Pollutants, Occupational↗

PubMed2005

Space-time super-resolution.

We propose a method for constructing a video sequence of high space-time resolution by combining information from multiple low-resolution video sequences of the same dynamic scene. Super-resolution is performed simultaneously in time and in space. By "temporal super-resolution," we mean recovering rapid dynamic events that occur faster than regular frame-rate. Such dynamic events are not visible (or else are observed incorrectly) in any of the input sequences, even if these are played in "slow-motion." The spatial and temporal dimensions are very different in nature, yet are interrelated. This leads to interesting visual trade-offs in time and space and to new video applications. These include: 1) treatment of spatial artifacts (e.g., motion-blur) by increasing the temporal resolution and 2) combination of input sequences of different space-time resolutions (e.g., NTSC, PAL, and even high quality still images) to generate a high quality video sequence. We further analyze and compare characteristics of temporal super-resolution to those of spatial super-resolution. These include: How many video cameras are needed to obtain increased resolution? What is the upper bound on resolution improvement via super-resolution? What is the temporal analogue to the spatial "ringing" effect?

Algorithms↗

PubMed1996

Computer-assisted interpretation of flow cytometry data in hematology.

A computer program has been developed for computer-assisted diagnosis (including subclassification) of flow cytometry data of acute leukaemias and non-Hodgkin lymphomas by means of artificial intelligence. The knowledge base for the system has been formulated as semantic networks that describe physiological hematopoiesis as well as the pathological situation (e.g., aberrant antigen expression) of hematological disorders. The semantic networks reflect the hierarchy of cells and their occurrence in diseases, the normal and pathological antigen expression patterns of cells, cell maturation, and the frequency of cell populations in normal blood and bone marrow. Using these semantic networks, the diagnosis algorithm compares the characteristic antigen expression pattern of a disease with the actual findings in the blood or bone marrow sample. The algorithm can separate mixed populations by taking double staining findings into account. Finally, a diagnosis text is generated that describes all identified cell populations and the resulting diagnosis. The validation of the program showed a correct diagnosis (disease group and subclassification) in 97% of the cases (n = 633) with slight differences between the disease groups (e.g., B-NHL: 99%, B-cell ALL: 84%).

Acute Disease↗

PubMed2005

Modeling the MHC class I pathway by combining predictions of proteasomal cleavage, TAP transport and MHC class I binding.

Epitopes presented by major histocompatibility complex (MHC) class I molecules are selected by a multi-step process. Here we present the first computational prediction of this process based on in vitro experiments characterizing proteasomal cleavage, transport by the transporter associated with antigen processing (TAP) and MHC class I binding. Our novel prediction method for proteasomal cleavages outperforms existing methods when tested on in vitro cleavage data. The analysis of our predictions for a new dataset consisting of 390 endogenously processed MHC class I ligands from cells with known proteasome composition shows that the immunological advantage of switching from constitutive to immunoproteasomes is mainly to suppress the creation of peptides in the cytosol that TAP cannot transport. Furthermore, we show that proteasomes are unlikely to generate MHC class I ligands with a C-terminal lysine residue, suggesting processing of these ligands by a different protease that may be tripeptidyl-peptidase II (TPPII).

ATP-Binding Cassette Transporters↗

PubMed2005

Text mining and ontologies in biomedicine: making sense of raw text.

The volume of biomedical literature is increasing at such a rate that it is becoming difficult to locate, retrieve and manage the reported information without text mining, which aims to automatically distill information, extract facts, discover implicit links and generate hypotheses relevant to user needs. Ontologies, as conceptual models, provide the necessary framework for semantic representation of textual information. The principal link between text and an ontology is terminology, which maps terms to domain-specific concepts. This paper summarises different approaches in which ontologies have been used for text-mining applications in biomedicine.

Abstracting and Indexing↗

PubMed2006

Function approximation using generalized adalines.

This paper proposes neural organization of generalized adalines (gadalines) for data driven function approximation. By generalizing the threshold function of adalines, we achieve the K-state transfer function of gadalines which responds a unitary vector of K binary values to the projection of a predictor on a receptive field. A generative component that uses the K-state activation of a gadaline to trigger K posterior independent normal variables is employed to emulate stochastic predictor-oriented target generation. The fitness of a generative component to a set of paired data mathematically translates to a mixed integer and linear programming. Since consisting of continuous and discrete variables, the mathematical framework is resolved by a hybrid of the mean field annealing and gradient descent methods. Following the leave-one-out learning strategy, the obtained learning method is extended for optimizing multiple generative components. The learning result leads to parameters of a deterministic gadaline network for function approximation. Numerical simulations further test the proposed learning method with paired data oriented from a variety of target functions. The result shows that the proposed learning method outperforms the MLP and RBF learning methods for data driven function approximation.

Algorithms↗

PubMed2005

Scalable model-based clustering for large databases based on data summarization.

The scalability problem in data mining involves the development of methods for handling large databases with limited computational resources such as memory and computation time. In this paper, two scalable clustering algorithms, bEMADS and gEMADS, are presented based on the Gaussian mixture model. Both summarize data into subclusters and then generate Gaussian mixtures from their data summaries. Their core algorithm, EMADS, is defined on data summaries and approximates the aggregate behavior of each subcluster of data under the Gaussian mixture model. EMADS is provably convergent. Experimental results substantiate that both algorithms can run several orders of magnitude faster than expectation-maximization with little loss of accuracy.

Algorithms↗

PubMed2004

Automatic sensor placement for model-based robot vision.

This paper presents a method for automatic sensor placement for model-based robot vision. In such a vision system, the sensor often needs to be moved from one pose to another around the object to observe all features of interest. This allows multiple three-dimensional (3-D) images to be taken from different vantage viewpoints. The task involves determination of the optimal sensor placements and a shortest path through these viewpoints. During the sensor planning, object features are resampled as individual points attached with surface normals. The optimal sensor placement graph is achieved by a genetic algorithm in which a min-max criterion is used for the evaluation. A shortest path is determined by Christofides algorithm. A Viewpoint Planner is developed to generate the sensor placement plan. It includes many functions, such as 3-D animation of the object geometry, sensor specification, initialization of the viewpoint number and their distribution, viewpoint evolution, shortest path computation, scene simulation of a specific viewpoint, parameter amendment. Experiments are also carried out on a real robot vision system to demonstrate the effectiveness of the proposed method.

Algorithms↗

PubMed2026

Leptospira-host interactions: advancing next-generation vaccines and diagnostics.

SUMMARYLeptospirosis, a widespread zoonotic disease caused by pathogenic Leptospira species, remains a major public health challenge, particularly in tropical and subtropical regions. Despite advances in understanding Leptospira biology and pathogenesis, effective disease control continues to be limited by the lack of rapid, early diagnostics, and broadly protective vaccines. This review comprehensively examines recent progress in deciphering Leptospira-host interactions, with emphasis on key virulence factors, immune-evasion mechanisms, and host immune responses that influence disease outcomes. Particular focus is placed on the molecular and cellular basis of adhesion, invasion, immune modulation, and persistent colonization. We further discuss the limitations of current vaccines and diagnostic approaches, and highlight how emerging technologies, including pan-genomics, proteomics, reverse vaccinology, immunoinformatics, and omics-based antigen discovery, are facilitating the development of next-generation vaccines and diagnostics. Finally, we outline major translational challenges and future perspectives for improving clinical management, surveillance, and prevention of leptospirosis. The concepts discussed in this review may also provide broader insights into vaccine and diagnostic development for other zoonotic bacterial infections.

Humans↗

PubMed2001

Recruitment learning of boolean functions in sparse random networks.

This work presents a new class of neural network models constrained by biological levels of sparsity and weight-precision, and employing only local weight updates. Concept learning is accomplished through the rapid recruitment of existing network knowledge - complex knowledge being realised as a combination of existing basis concepts. Prior network knowledge is here obtained through the random generation of feedforward networks, with the resulting concept library tailored through distributional bias to suit a particular target class. Learning is exclusively local - through supervised Hebbian and Winnow updates - avoiding the necessity for backpropagation of error and allowing remarkably rapid learning. The approach is demonstrated upon concepts of varying difficulty, culminating in the well-known Monks and LED benchmark problems.

Algorithms↗

PubMed2006

NOXclass: prediction of protein-protein interaction types.

BACKGROUND: Structural models determined by X-ray crystallography play a central role in understanding protein-protein interactions at the molecular level. Interpretation of these models requires the distinction between non-specific crystal packing contacts and biologically relevant interactions. This has been investigated previously and classification approaches have been proposed. However, less attention has been devoted to distinguishing different types of biological interactions. These interactions are classified as obligate and non-obligate according to the effect of the complex formation on the stability of the protomers. So far no automatic classification methods for distinguishing obligate, non-obligate and crystal packing interactions have been made available. RESULTS: Six interface properties have been investigated on a dataset of 243 protein interactions. The six properties have been combined using a support vector machine algorithm, resulting in NOXclass, a classifier for distinguishing obligate, non-obligate and crystal packing interactions. We achieve an accuracy of 91.8% for the classification of these three types of interactions using a leave-one-out cross-validation procedure. CONCLUSION: NOXclass allows the interpretation and analysis of protein quaternary structures. In particular, it generates testable hypotheses regarding the nature of protein-protein interactions, when experimental results are not available. We expect this server will benefit the users of protein structural models, as well as protein crystallographers and NMR spectroscopists. A web server based on the method and the datasets used in this study are available at http://noxclass.bioinf.mpi-inf.mpg.de/.

Algorithms↗