Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Pattern Recognition, Automated”

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 91 records · Page 5Linked to original sources
PubMed1993

Computerized pattern recognition of EEG artifact.

Automated artifact classification of quantified EEG (QEEG) epochs from 9 males using linear discriminant analysis showed greater than 85% agreement with judges' opinions. These results were replicated (n = 600 epochs for each sample). Testing the entire sample (n = 5800) illustrated reliable eye artifact (94%) but reduced muscle artifact classification (70%) accuracy. Agreement was lowest in the case of more subtle forms of muscle artifact (i.e., low amplitude muscle), however, less than 4% of these were wrongly classified as non-artifact. Improved data collection techniques retaining high frequency energies are anticipated to improve muscle artifact recognition. Results indicate that low levels of artifact contamination would result when only those epochs classified as non-artifact were accepted for inclusion in further analysis.

Blinking↗
PubMed1999

New approaches for the detection and analysis of electroencephalographic burst-suppression patterns in patients under sedation.

An automatic EEG pattern detection unit was developed and tested for the recognition of burst-suppression periods and for the separation of burst from suppression patterns. The median, standard deviation and the 95% edge frequency were computed from single channels of the EEG within a moving window and completed by the continuous computation of frequency band power via an adapted Hilbert resonance filter. These parameters were given to the inputs of two hierarchically arranged artificial neural networks (NNs). The output signals of NNs indicate the suppression and burst phases. The burst recognition was focused on the precise recognition of the burst onset. In subsequent processing steps the time course of percentages of burst patterns within their corresponding burst-suppression-phases was calculated and the time locations of burst onsets can be used to trigger an averaging for a burst-related analysis. The data for our investigations were derived from the routine EEG derivations of 12 patients with various neurosurgical diseases. A group-related training of the NNs was realized. For the group-related trained NNs EEG data for 6 patients were used for training and the data of 6 other patients for testing the classification performance of the pattern recognition units. Additionally, the reliability of the detection algorithm was tested with data of two patients with convulsive state, resistant to treatment, and burst-suppression like pattern EEC.

Adolescent↗
PubMed2000

Pattern recognition analysis of endogenous cell metabolites for high throughput mode of action identification: removing the postscreening dilemma associated with whole-organism high throughput screening.

Although whole-organism HTS can give clear indications of in vivo activity, typically few clues are given as to the mechanism of action (MOA), and determining the MOA for large numbers of active compounds can be costly and complex-an alternative approach is required. This report demonstrates that it is possible to conduct relatively high throughput MOA characterization of HTS hits utilizing a single sample preparation and analytical method. By monitoring a wide range of endogenous cellular metabolites via (1)H nuclear magnetic resonance spectroscopy, the MOA of herbicides can be predicted using computational methods to compare the metabolite perturbation patterns. Herbicides that induce a characteristic pattern of metabolic perturbation in maize include inhibitors of acetolactate synthase, acetyl co-enzyme A carboxylase, protoporphyrinogen oxidase, 5-enolpyruvylshikimate-3-phosphate synthase, and phytoene desaturase. In soya, photosystem II inhibitors can also be detected, further demonstrating that this method is not limited to inhibitors of enzymes that directly act upon endogenous metabolites, or a single species. The methods, including data analysis, can be readily automated, enabling relatively high throughput MOA elucidation of whole-organism screen hits. Additionally, for compounds with a novel MOA, this approach may lead to MOA identification faster than traditional methods. It is envisaged that application of these data analysis methods to other data types-for example, transcription (mRNA) or translation (protein) profiles-is likely to permit higher throughput with smaller sample requirements, along with ability to discriminate MOAs that are not adequately discriminated based upon endogenous metabolite profiles.

Automation↗
PubMed1999

Application of a fuzzy pattern classifier to decision making in portal verification of radiotherapy.

With the large volume of electronic portal images acquired and stringent time constraints, it is no longer feasible to follow the convention whereby the radiation oncologist reviews and approves or rejects all portals. For that purpose we have developed a portal image classifier based on the fuzzy k-nearest neighbour (k-NN) algorithm. Each portal image is represented by a feature vector that consists of translational and rotational errors in the placement of radiation field borders that were measured in the portal image. Memberships in the acceptable portal class for the reference portal images within a training dataset were defined by a radiation oncologist expert. The fuzzy k-NN portal image classifier was trained and tested on a dataset of 328 portal images acquired during tangential irradiations of the breast. The memberships in the acceptable portal class produced by the fuzzy k-NN algorithm agreed very well with those defined by the expert. The linear correlation coefficient was equal to 0.89. Performance of the fuzzy k-NN classifier was also evaluated from the portal decision-making point of view using the measures of accuracy, sensitivity and specificity. The fuzzy k-NN portal classifier was capable of identifying almost all the truly unacceptable portals with an acceptably low false alarm rate.

Artificial Intelligence↗
PubMed2002

Automated main-chain model building by template matching and iterative fragment extension.

An algorithm for the automated macromolecular model building of polypeptide backbones is described. The procedure is hierarchical. In the initial stages, many overlapping polypeptide fragments are built. In subsequent stages, the fragments are extended and then connected. Identification of the locations of helical and beta-strand regions is carried out by FFT-based template matching. Fragment libraries of helices and beta-strands from refined protein structures are then positioned at the potential locations of helices and strands and the longest segments that fit the electron-density map are chosen. The helices and strands are then extended using fragment libraries consisting of sequences three amino acids long derived from refined protein structures. The resulting segments of polypeptide chain are then connected by choosing those which overlap at two or more C(alpha) positions. The fully automated procedure has been implemented in RESOLVE and is capable of model building at resolutions as low as 3.5 A. The algorithm is useful for building a preliminary main-chain model that can serve as a basis for refinement and side-chain addition.

Algorithms↗
PubMed2001

ERS transform for the automated detection of bronchial abnormalities on CT of the lungs.

The identification of bronchi on Computed Tomography (CT) images of the lungs provides valuable clinical information in patients with suspected airways diseases including bronchiectasis, emphysema, or constrictive obliterative bronchiolitis. The automated recognition of the airways is, therefore, an important part of a diagnosis aid system for resolving potential ambiguities associated with intensity-based feature extractors. On CT images, near-perpendicular cross sections of bronchi normally appear as elliptical rings and this paper presents a novel technique for their recognition. The proposed method, the edge-radius-symmetry (ERS) transform, is based on the analysis of the distribution of edges in local polar coordinates. Pixels are ranked according to local edge (E) strength, radial (R), uniformity and local symmetry (S). A discrete implementation of the technique is provided which reduces the computational cost of the ERS transform by using a geometric approximation of the intensity patterns. The identification of the adjacent pulmonary vessels with template matching then allows for the automated measurement of bronchial dilatation and bronchial wall thickening. Computationally, the method compares favorably with other methods such as the Hough transform. Noise-sensitivity of the technique was evaluated on a set of synthetic images and nine patients under investigation for suspected airways disease. Agreement for the automated scoring of the presence and severity of bronchial abnormalities was demonstrated to be comparable to that of an experienced radiologist (kappa statistics kappa > 0.5 ).

Bronchial Diseases↗
PubMed1977

A software system to record and analyze digitized cell images.

This paper describes basic software for digitization and processing of microscopic cell images used at the Department of Clinical Cytology at Uppsala University Hospital. A family of programs running on a PDP-8 minicomputer which is connected to a Leitz Orthoplan microscope with two image scanners, one diode-array scanner and a moving-stage photometer, is used for data collection. The digitized image data is converted by converted by conversion program to IBM compatible format. The data structures for image processing and statistical evaluation on the IBM system are also described. Finally, some experiences from the use of the software in cytology automation are discussed.

Cell Biology↗
PubMed1998

Automatic on-line one-channel recognition of masseter activity.

The etiology of myoarthropathies of the masticatory system (MAP) is not fully understood. For the hypothetical association between the myogenous pain of MAP patients and masticatory muscle overuse to be proved, functional and parafunctional behavior of the masticatory muscles should be analyzed in normal and diseased subjects. The aim of this study was to test on-line the validity and reliability of an algorithm, applied to the electromyographic signal, to recognize various oral activities. The surface electromyogram of the masseter muscle was recorded in 12 subjects (seven females and five males, from 18 to 32 years old) who performed a series of functional and parafunctional activities (chewing soft food, chewing hard food, swallowing, laughing, speaking, and tooth grinding and clenching), as well as no activity. During the computer training phase, intra-individual classification functions of a multivariate discriminant analysis were calculated while each subject performed the described activities. During the test phase, each subject repeated the same activities, and the computer continuously classified them on-line. The percentage of correctly recognized activities was calculated for each activity and for each subject. No activity, chewing hard food, swallowing, laughing, grinding, and clenching were recognized correctly > 99% of the time. Chewing soft food was recognized correctly 97% and speaking 86% of the time. The sensitivity values for the recognition rates of the complete oral activities were, with one exception, > 0.82; the specificity values were > 0.95, and the kappa-values > 0.80. These results show that the algorithm had high sensitivity, specificity, and reliability in the classification of different oral activities under laboratory conditions.

Adolescent↗
PubMed2001

Automatic scoliosis detection based on local centroids evaluation on moiré topographic images of human backs.

This paper presents a technique for automating human scoliosis detection by computer based on moiré topographic images of human backs. Scoliosis is a serious disease often suffered by teenagers. For prevention, screening is performed at schools in Japan employing a moiré method in which doctors inspect moiré images of subjects' backs visually. The inspection of a large number of moiré images collected by the school screening causes exhaustion of doctors and leads to misjudgment. Computer-aided diagnosis of scoliosis has, therefore, been requested eagerly by orthopedists. To automate the inspection process, unlike existent three-dimensional techniques, displacement of local centroids is evaluated two-dimensionally between the left-hand side and the right-hand side of the moiré images in the present technique. The technique was applied to real moiré images to draw a distinction between normal and abnormal cases. According to the leave-out method, the entire 120 image data (60 normal and 60 abnormal) were separated into three data sets. The linear discriminant function based on Mahalanobis distance was defined on the two-dimensional feature space employing one of the data sets containing 40 moiré images and classified 80 images in the remaining two sets. The technique finally achieved the average classification rate of 88.3%.

Algorithms↗