SEARCH · Search PubMed

Results for “Feature selection”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,495 records · Page 83Linked to original sources

PubMed1995

Neural mechanisms for stimulus selection in cortical areas of the macaque subserving object vision.

The present article reviews some recent work on the neuronal mechanisms underlying space-based and feature-based stimulus selection in the primate occipito-temporal pathway of cortical visual processing. Clear evidence demonstrates that activity in areas V4 and IT is high for a stimulus which is selected either for its position in space or for its features, while it is considerably suppressed for other, irrelevant stimuli. Data are discussed within a conceptual framework whereby objects in the visual field always compete for focal resources. According to task demands, any kind of input (objects of a certain category, objects with a certain form, color or motion, objects at a certain location) can be behaviorally relevant. A short-term description (working memory) of the currently relevant object properties controls competitive bias in the visual system, such that inputs matching that description are favored to the disadvantage of task-irrelevant inputs. This framework emphasizes a tight, causal link between memory signals and mechanisms for stimulus selection in visual cortex. In all cases gating of neural activity was constrained by spatial factors. In area V4, responses to an ignored stimulus in the receptive field of the recorded neuron were maximally suppressed when the monkey attended to a second stimulus located within the boundary of the same receptive field, while suppression was virtually absent when attention was directed to a second stimulus well outside the receptive field border. In IT cortex, suppressed responses depended on both the selected and ignored stimuli being within the hemifield contralateral to the recorded hemisphere, while suppression was much reduced when the stimuli were presented across the vertical midline. These spatial constraints on the occurrence of modulation of visual responses may reflect limitations imposed by the local pattern of reciprocal inhibitory connections, which are supposed to underlie competitive interactions among objects in the field, that is among object representations in cortex.

Animals↗

PubMed1992

Dysgraphia and selective impairment of the graphemic buffer.

We report the linguistic analysis of a case of pure dysgraphia whose features suggest a selective deficit of the graphemic buffer. We discuss the neuropsychological pattern in the light of theoretical models of the cognitive processes considered to underlie writing skills.

Aged↗

PubMed1991

Selective attention modulates extrastriate visual regions in humans during visual feature discrimination and recognition.

Positron emission tomography (PET) was used to identify regions of the human visual system which were selectively modulated by attention during feature discrimination and recognition tasks. In a first experiment, subjects were cued to the shape, colour or speed of visual stimulus arrays during a same-different match-to-sample paradigm. The psychophysical sensitivity for discriminating subtle attribute variations was enhanced by selective attention. Correspondingly, the neural activity (as measured by blood flow changes) in different visual associative regions was enhanced when subjects attended to different attributes of the same stimulus (intraparietal sulcus for speed; collateral sulcus and dorsolateral occipital cortex for colour; collateral sulcus, fusiform and parahippocampal gyri, superior temporal sulcus for shape). These regions appeared to be specialized for processing the selected attribute. Attention to a visual feature, therefore, enhances the psychophysical sensitivity as well as the neural activity of specialized processing regions of the human visual system. In a second experiment the effect of target probability (which biases attentional selection) was studied during visual search tasks involving the recognition of a single-feature (i.e. colour) or a feature-conjunction (i.e. colour x orientation) target. Target probability positively modulated neural activity of extrastriate visual regions, which were related to the single-feature or feature-conjunction processing level. These results suggest that selective attention can influence different processing levels in the visual system, possibly reflecting a facilitatory effect on different visual computations or task components.

Attention↗

PubMed2004

Investigation of the electrophysiological properties of enniatins.

Enniatins are cyclohexadepsipeptides produced by various species of the genus Fusarium, and are known to have ionophoric, antibiotic, and in vitro hypolipidaemic properties. With the patch clamp technique in the inside-out mode it could be shown that enniatin easily incorporates into the cell membrane in which it forms cation-selective pores. This feature is characterized by unitary transitions to conductance levels typical for channels, ion selectivity, rectification, conductivity in the pS range, and block. A model of vertically stacked enniatin molecules that form sandwich complexes is suggested. Like gramicidin enniatin is a passive channel. Single channel properties for the isomers enniatin A1, B, and B1 differed from each other. This implies an influence of the substituted moieties on the complexation of cations. Electrical activity was followed by changes in intracellular ion concentrations, which are consistent with depolarization of the membrane resting potential, shortening of action potential duration, and reduced contractility.

Action Potentials↗

PubMed2003

Neural mechanisms of top-down control during spatial and feature attention.

Theories of visual selective attention posit that both spatial location and nonspatial stimulus features (e.g., color) are elementary dimensions on which top-down attentional control mechanisms can selectively influence visual processing. Neuropsychological and neuroimaging studies have demonstrated that regions of superior frontal and parietal cortex are critically involved in the control of visual-spatial attention. This frontoparietal control network has also been found to be activated when attention is oriented to nonspatial stimulus features (e.g., motion). To test the generality of the frontoparietal network in attentional control, we directly compared spatial and nonspatial attention in a cuing paradigm. Event-related fMRI methods permitted the isolation of attentional control activity during orienting to a location or to a nonspatial stimulus feature (color). Portions of the frontoparietal network were commonly activated to the spatial and nonspatial cues. However, direct statistical comparisons of cue-related activity revealed subregions of the frontoparietal network that were significantly more active during spatial than nonspatial orienting when all other stimulus, task, and attentional factors were equated. No regions of the frontal-parietal network were more active for nonspatial cues in comparison to spatial cues. These findings support models suggesting that subregions of the frontal-parietal network are highly specific for controlling spatial selective attention.

Adult↗

PubMed1996

Pharmacophore development for antagonists at alpha 1 adrenergic receptor subtypes.

Many receptors, including alpha 1 adrenergic receptors, have a range of subtypes. This offers possibilities for the development of highly selective antagonists with potentially fewer detrimental effects. Antagonists developed for alpha 1A receptors, for example, would have potential in the treatment of benign prostatic hyperplasia. As part of the molecular design process, structural features necessary for the selective affinity for alpha 1A and alpha 1B adrenergic receptors have been investigated. The molecular modelling software (particularly the Apex module) of Molecular Simulations, Inc. was used to develop pharmacophore models for these two subtypes. Low-energy conformations of a set of known antagonists were used as input, together with a classification of the receptor affinity data. The biophores proposed by the program were evaluated and pharmacophores were proposed. The pharmacophore models were validated by testing the fit of known antagonists, not included in the training set. The critical structural feature for selectivity between the alpha 1A and alpha 1B adrenergic receptor sites is the distance between the basic nitrogen atom and the centre of an aromatic ring system. This will be exploited in the design and synthesis of structurally new selective antagonists for these sites.

Adrenergic alpha-1 Receptor Antagonists↗

PubMed1986

Prognosis and prediction of outcome in comatose head injured patients.

Recent studies on the prognosis of comatose head injured patients have identified single powerful prognostic features at various time points during the first month after onset of coma. Using appropriate statistical methods even more powerful combinations of prognostic features can be selected. At each time point, optimal prediction requires sets of only 3 to 5 features. These features include depth and duration of coma as assessed by the Glasgow Coma Scale, pupil reactivity to light, age in decades, and spontaneous and reflex eye movements. In individual new patients, bedside predictions are now possible, e.g. using a booklet with prognosis tables like the one used in Rotterdam. Doctors actually learn by using these tables as they retain some of the information. However, the main application is that these tables permit one to evaluate whether differences in survival rates in different centres with different management regimes are due to a difference in management efficacy or to a difference in initial severity of injury.

Coma↗

PubMed1995

Positive selection of T cells.

In the past year, significant technical developments have provided the opportunity to investigate the more mechanistic features of positive selection. Major progress has been made in determining the structure and function of the early pre-T cell receptor, in defining cell types that mediate positive selection, and in analyzing the contribution of MHC and co-receptors to CD4/CD8 lineage commitment. The most revealing studies have been those addressing the role of peptides in thymic selection.

Animals↗

PubMed2002

Gender selection: ethical, scientific, legal, and practical issues.

PURPOSE: This work offers an overview of the technology available and assisted reproductive technology (ART) practitioner attitudes to human reproductive sex preselection in either sperm with the use of flow cytometry (FC) or in embryos by means of preimplantational genetic diagnose (PGD) together with an analysis of Spanish legal environment. METHODS: A review of the legal, ethical and technical literature of the methods to select the sex in the offspring is performed. RESULTS: Sex selection in humans has different utilities to be employed depending on each country's law. Moreover, different ethical concerns are raised depending on the type of sex selection, in sperm or embryos. Both methodologies to pre-select the sex are trustworthy, with a high predictive power in the determination of the sex, but nevertheless, PGD is better than FC selection in this aspect. CONCLUSIONS: After a careful analysis of ethical, legal, and scientific features of gender selection, FC combined with PGD appears to be the most acceptable way to select the sex of the progeny whatever the circumstances are.

Female↗

PubMed2003

Feature extraction for the analysis of colon status from the endoscopic images.

BACKGROUND: Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status. METHODS: Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA) and are evaluated using Backpropagation Neural Network (BPNN). RESULTS: Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (tau = 1%), is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, tau = 1%) or color (90.52%, tau = 1%) features. CONCLUSION: In conclusion, novel methods for extracting new texture- and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.

Colon↗

PubMed2025

Accurate identification of abnormal ploidy using an artificial intelligence model in preimplantation genetic testing.

STUDY QUESTION: Can ultra-low-coverage whole-genome sequencing (ulc-WGS) accurately identify abnormal ploidy during preimplantation genetic testing (PGT)? SUMMARY ANSWER: The artificial intelligence (AI)-based PGT-Plus model demonstrates high accuracy in ploidy detection, offering a cost-effective solution that enhances clinical utility of PGT. WHAT IS KNOWN ALREADY: The predominant PGT for aneuploidy can identify chromosomal aneuploidies but cannot determine ploidy status. Transferring embryos with ploidy abnormalities can result in miscarriage and molar pregnancy. On the other hand, in ART, fertilization is assessed by morphological pronuclear assessment at the zygote stage. However, it has a low specificity in the prediction of abnormal ploidy status and embryos deemed abnormally fertilized can yield healthy pregnancies. Accurately identified abnormal ploidy in PGT-A can resolve current limitations and expand the utility range of PGT-A. Several studies have identified ploidy abnormalities; however, they were mainly based on single-nucleotide polymorphism (SNP) arrays or needed to combine additional targeted-next-generation sequencing (NGS) information. Studies based on ulc-WGS remain scarce. STUDY DESIGN SIZE DURATION: The study consisted of two stages: methodology establishment and validation. An AI model, named PGT-Plus, was developed using 653 samples with known ploidy status, which was further validated using 792 different ploidy status samples. In the clinical application stage, the approach was used to analyse the ploidy status of 19 103 normally fertilized PGT blastocysts and 140 single pronucleus (1PN)-derived blastocysts collected between May 2022 and December 2023. All blastocysts were tested using trophectoderm biopsy and NGS. PARTICIPANTS/MATERIALS SETTING METHODS: The methodology is based on the ulc-WGS data. First, based on samples with known ploidy status: the heterozygosity rate of high-frequency biallelic SNPs, the likelihood ratio (LLR) of alleles was calculated under different assumptions ('both parental homologs' [BPH] from a single parent, 'single parental homolog' [SPH] from each parent, disomy, and monosomy) by leveraging allele frequencies and linkage disequilibrium (LD) measured in the 1000 genomes project database. Twenty-three continuous candidate features derived from heterozygosity rates and LLRs of chromosomes or selected windows were included to establish the ploidy prediction AI model. Gini importance analysis and multicollinearity mitigation was performed for feature selection, then the performance of Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression for modelling was compared. Subsequently, the parameter optimization was performed based on the RF model. Ploidy constitution concordance was evaluated in known ploidy status samples. The frequency of abnormal ploidy in normal fertilized PGT blastocysts and 1PN-derived blastocysts (including conventional IVF and ICSI) was evaluated. MAIN RESULTS AND THE ROLE OF CHANCE: Eleven features were collected for model architecture compared to SVM and Logistic Regression; RF achieved superior performance for ploidy detection. The AI model achieved an AUC of 1 for genome-wide-uniparental diploidy (GW-UPD), 1 for triploidy, and 0.99 for diploidy. For the 792 validation samples, 99.5% of samples were successfully detected using the AI model, and the model showed 100% accuracy for ploidy classification. In the clinical application stage, out of 19 103 PGT samples, 19 069 were successfully analysed using the model, with 110 (0.57%) identified as having abnormal ploidy embryos. Among these, 12.7% (14/110) were identified as GW-UPD, and 87.3% (96/110) were triploid. Among 5563 diploid blastocysts transferred, 3478 clinical pregnancies were achieved. Subsequent ploidy analysis was performed for 217 spontaneous abortion and 935 prenatal diagnostic samples, and no abnormal ploidy was identified. Furthermore, of the 140 1PN embryos tested, 40 (28.6%) exhibited GW-UPD, 3 (2.1%) exhibited triploidy, and 97 (69.3%) were determined to be biparental and normally fertilized. Among the 97 biparental embryos, 46 were diploid, 11 were mosaic, and 40 were aneuploid. In terms of the insemination pattern, the percentage of abnormal ploidy in ICSI was significantly higher than in conventional IVF (P < 0.01, 37.1% vs. 2.9%, respectively). With full informed consent, 20 patients without euploidy from normal fertilization chose 1PN-derived biparental and diploid blastocysts to transfer, resulting in 10 clinical pregnancies and 9 ongoing pregnancies. LARGE-SCALE DATA: N/A. LIMITATIONS REASONS FOR CAUTION: Some rare ploidy abnormalities, such as polyploidy with an equal number of identical sets of chromosomes and ploidy mosaicism cannot be accurately identified. Moreover, the origin of abnormal ploidy was not identified due to the unavailability of DNA from both parents. WIDER IMPLICATIONS OF THE FINDINGS: The PGT-Plus AI model provides a ploidy evaluation method based on the conventional PGT-A data and integrates directly into standard PGT-A workflows. Clinical utility results suggest that the model is a valuable tool for identifying embryos with abnormal ploidy in PGT-A and rescuing normal diploid embryos from abnormally fertilized embryos. These findings demonstrate that PGT-Plus significantly enhances the diagnostic accuracy of PGT. STUDY FUNDING/COMPETING INTERESTS: This study was supported by grants from Major Scientific Program of CITIC Group (No. 2023ZXKYB34100, to Ge.L.), Hunan Provincial Grant for Innovative Province Construction (2019SK4012), Hunan Xiangjiang New District (Changsha High-tech Zone) key core technology research project in 2023, and Science Foundation of Hunan Province (Grant 2023JJ30422). All authors declared no conflicts of interest..

artificial intelligence↗

PubMed1981

Effects of camera cuts and music on selective attention and verbal and motor imitation by mentally retarded adults.

Effects of experimentally manipulating camera cuts (high vs. low frequency) and music (present vs. absent) on total and selective visual attention to and imitation of prosocial TV programs were examined. Subjects were 96 adults (mean IQ = 46). Within programs, selective viewing of content features (dialogue, distress, helping, and reinforcement) and media features (music, cuts, zooms, and scene changes) were examined. Subjects selectively attended to cuts and zooms and all four content features. High-cuts frequencies in a program reduced selective attention and subsequent verbal imitation. There were no significant effects for music.

Adult↗

PubMed1977

Combination flap closure of facial defects.

In the past, combining local flaps to close skin defects has emphasized the shape of the defect. Combining local flaps on the basis of facial features and available donor skin has clear-cut advantages over single flap and regional flap closures in selected cases. Facial features may be more readily preserved and incision lines more easily disguised. A successful functional and cosmetic result is dependent on flap selection and design, as well as meticulous handling of skin and closure technics.

Basal Cell Carcinoma↗

PubMed1991

On the complexity of self.

Self peptides bound to self major histocompatibility complex (MHC) molecules have been implicated both in positive and in negative selection of T cells during intrathymic development. We report here that the novel MHC-restricted monoclonal antibody Y-Ae detects the MHC class II bound form of a major self peptide. Y-Ae binds approximately 12% of the relevant MHC class II molecules on self antigen presenting cells. The peptide detected by Y-Ae is one of several major peptides eluted from the MHC molecule. These data suggest that self peptides presented by self MHC class II molecules at densities sufficient to signal a CD4 T cell are of very limited complexity. Furthermore, as Y-Ae stains antigen presenting cells that mediate negative selection but not thymic cortical epithelial cells that drive positive selection, differential expression of self peptide:self MHC class II complexes may be a key feature of intrathymic selection.

Amino Acid Sequence↗

PubMed1987

Minima equalization: a useful strategy in automatic processing of microscopic images.

Specifically stained features in microscopic images rarely have a unique range of grey levels which would permit selection of the features by simple thresholding. The spaces between features and immediately surrounding them are often as dark or darker than the more lightly stained features. An algorithm for minima equalization which facilitates the extraction and segmentation of such features was designed and is explained in intuitive terms. It is applied to the analysis of cross-sections of peripheral myelinated nerve fibers. It is shown that the binary image obtained can be combined with a gradient image to give a binary image which accurately reflects the thickness of the myelin in the original image. Using silver-impregnated nerve endings and bile canaliculi stained for thiamine pyrophosphatase, binary images like those prepared manually from thick specimens using a camera lucida can be obtained using the minima equalization procedure. The image processor is used to develop a composite image by combining images at various focal planes through the thick specimen. This image is then processed to obtain the binary image.

Bile Canaliculi↗

PubMed2006

Robust sequence selection method used to develop the FluChip diagnostic microarray for influenza virus.

DNA microarrays have proven to be powerful tools for gene expression analyses and are becoming increasingly attractive for diagnostic applications, e.g., for virus identification and subtyping. The selection of appropriate sequences for use on a microarray poses a challenge, particularly for highly mutable organisms such as influenza viruses, human immunodeficiency viruses, and hepatitis C viruses. The goal of this work was to develop an efficient method for mining large databases in order to identify regions of conservation in the influenza virus genome. From these regions of conservation, capture and label sequences capable of discriminating between different viral types and subtypes were selected. The salient features of the method were the use of phylogenetic trees for data reduction and the selection of a relatively small number of capture and label sequences capable of identifying a broad spectrum of influenza viruses. A detailed experimental evaluation of the selected sequences is described in a companion paper. The software is freely available under the General Public License at http://www.colorado.edu/chemistry/RGHP/software/.

Computational Biology↗

PubMed2005

Bulk acousto-optic wavelength agile filter module for a wavelength-multiplexed optical scanner.

An acousto-optic tunable filter-based wavelength-selection module with features optimized for a wavelength-multiplexed optical scanner (W-MOS) is proposed and demonstrated. The W-MOS produces high-speed multiple scan beams if it is engaged with an agile tunable source with multiwavelength generation capability. In particular, the proposed fiber-connected module features high-speed, low-loss, narrow-linewidth, and single-multiple wavelength selection by means of radio frequency drive signal control for single- or multiple-beam scan operations. The unique module offers input laser beam power control that in turn delivers the desired scanned laser beam power shaping. Experimental results match module design theory and demonstrate a fast 5.4-micros wavelength selection speed, a low (1.53-dB) fiber-to-fiber optical insertion loss, a 5.55-nm 3-dB spectral width, and a 1500-1600-nm agile wavelength operational band.

Journal Article↗

PubMed1999

The FeatureGate model of visual selection.

The model presented here is an attempt to explain the results from a number of different studies in visual attention, including parallel feature searches and serial conjunction searches. Variations in such slope with variations in feature contrast and individual subject differences, attentional gradients triggered by cueing, feature-driven spatial selection, split attention, inhibition of distractor locations, and flanking inhibition. The model is implemented in a neural network consisting of a hierarchy of spatial maps. Attentional gates control the flow of information from each level of the hierarchy to the next. The gates are jointly controlled by a Bottom-Up System favoring locations with unique features and a Top-Down System favoring locations with features designated as target features. Because the gating of each location depends on the features presented there, the model is called FeatureGate.

Attention↗