PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Pattern Recognition, Automated”

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 127 records · Page 7Linked to original sources
PubMed1997

Computerized analysis of daily life motor activity for ambulatory monitoring.

The primary goal of an ambulatory monitoring of motor activities (AMMA) system is to document the occurrence of random and spontaneous motor activities (e.g., sitting, lying, standing, walking, running, etc.) of the ambulatory subject in natural environmental circumstances. Much progress has been made in recording fidelity, reduction in energy requirement, fixation of the accelerometers, equipment size and weight, memory capacity and data acquisition. At present, our laboratory is interested in developing an automated off-line AMMA-signal analysis system. The system has to take care of activity (wave) detection, recognition of onsets and endpoints of the various activities (waves), and computation of a set of relevant clinical parameters (e.g., total walking time, number of times rising from a chair, etc.) from long-term recorded data. Two methods are currently being used for computerizing the off-line analysis system: using an artificial neural network and using a set of selected features extracted from the input data. The present paper is aimed at the latter method. The method was successfully applied to long-term recorded data sets of eight male amputees and three other subjects. The primary results indicate that the method is a potentially useful too to computerize the off-line analysis system.

Activities of Daily Living↗
PubMed1981

TULIPS: the Uppsala-Linkoping Image Processing System.

The Uppsala-Linkoping Image Processing System, TULIPS, is described. TULIPS, a hardware-software system designed for cell image processing, was developed at Uppsala University Hospital in cooperation with the Department of Electrical Engineering at Linkoping University. The hardware part of the image processing system is built around a high-speed data bus with a capacity of about 40 M byte/sec connected to a PDP-11/55 host computer. An image memory, an LSI-11 microcomputer and a video interface for displaying the image memory content on a TV monitor are also connected to the high-speed bus. An automated microscope and a "Poulsen processor" for low resolution segmentation, both to be attached to the high-speed bus, are being developed. A monitor and an interpreter for an image processing language have been implemented on the host computer. This software system allows interactive, as well as batch, processing. The degree of user interaction is easily adapted to the user's needs. The image processing language is command oriented, and it is easily expanded by adding new commands. The system has been used both for studies in the field of quantitative microscopy and as a platform for development and testing of new image processing algorithms.

Computers↗
PubMedDate not supplied

Automatic registration of multiple skin lesions by use of point pattern matching.

Computerized comparison of serial skin images is a potentially valuable tool for melanoma screening. In automating this process, matching or "registering" each lesion in a pair of images plays an important role in looking for clinically significant change. We have investigated three practical techniques--a point pattern correlation, a 2-point geometrical transformation, and a 3-point geometrical transformation--for their effectiveness in matching and identifying lesions in pairs of skin images. These techniques view the spots in each image as a point pattern to be matched from image to image. Each of these methods is shown to be quite effective as long as one or more known initial match points can be provided. Experiments performed by imaging actual patients under realistic conditions indicate that the 3-point transformation algorithm performs the best overall, achieving an average matching accuracy of 97%. The nature of these algorithms, their relative performance under a range of conditions, and possible methods for improving accuracies are discussed.

Algorithms↗
PubMed1992

Diagnosing periapical bone lesions on radiographs by means of texture analysis.

Trabecular pattern, the radiographic projection of trabecular bone, is a repeated structure that appears in a dental radiograph. Texture analysis, the computer image analysis of repeated patterns, is a technique that can be used to automate the diagnosis of periapical lesions with the detection of the absence of the texture that corresponds to the trabecular bone. The purpose of this study was to determine whether it is feasible to use texture analysis to identify the presence of the trabecular pattern in radiographs and to detect a periapical bone lesion based on a local absence of this pattern. Thirty-two mandibular periapical films, 16 with and 16 without periapical lesions, were used in this study. Texture analysis was carried out on the digital images of these radiographs. In the 16 films with lesions, they were all correctly identified, and no lesions were found in the 16 films without lesions. This result is based on the a prior knowledge of the user about the localization of the disease. Locating periapical regions without user interaction is a goal for future research.

Alveolar Process↗
PubMedDate not supplied

Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information within an expert system.

The authors are developing an expert-system electrocardiogram (ECG) arrhythmia detector (HOBBES) for automated, long-term rhythm analysis. HOBBES employs rules and procedures that emulate how human experts analyze ECGs. This paper describes methods that HOBBES employs for improving error detection and correction in processing noisy ECGs. During periods of clean data, HOBBES develops a knowledge base that describes typical beat shapes, typical interbeat intervals between beats of different types, and patterns of beat sequences that it has observed. During periods of noisy data, HOBBES applies the information learned from the clean data to reject artifact and classify beats. HOBBES was evaluated in a noise-stress test using 35 half-hour ECG records containing a mixture of supraventricular and ventricular ectopy in normal sinus rhythm. In comparison with a classical arrhythmia detector (ARISTOTLE), HOBBES increased the number of correctly classified beats and enhanced the rejection of artifact.

Arrhythmias, Cardiac↗
PubMed1993

A knowledge based interpretation system for EMG abnormalities.

The conventional method of diagnosis in electromyography is complex and time consuming, not only due to the large number of parameters, to be considered for diagnosis, but also because of the usual procedure of evaluating the different parameters of EMG signal by visual scanning of the plotted signal. So there is a clear need to make use of computer aided decision support system. In the present work an attempt has been made in the direction of integration into one automated system, the qualitative knowledge of the physician, with possibly sophisticated signal analysis tools which must replace the visual scanning. A software program (in Turbo-C) on a PC-AT has been developed to evaluate the different parameters of MUAP's (motor unit action potential) in a EMG signal. Then an Expert system (in Turbo-Prolog) has been implemented for diagnostic purposes of different muscular abnormalities by making a knowledge base from the different parameters involved in the decision making procedure of clinical electromyography. A hybrid model of rule and frame based Expert system is implemented. An attempt has been made for making a complete system, i.e., for recording, analysis and decision making for diagnosis.

Diagnosis, Computer-Assisted↗
PubMed1997

Automated detection of hereditary syndromes using data mining.

Computer-based data mining methodology applied to family history clinical data can algorithmically create highly accurate, clinically oriented hereditary disease pattern recognizers. For the example of hereditary colon cancer, the data mining's selection of relevant factors to assess for hereditary colon cancer was statistically significant (P < 0.05). All final recognizer-formulated patterns of hereditary colon cancer were independently confirmed by a clinical expert. Applied to previously analyzed family histories, the recognizer identified the definitive hereditary histories, correctly responded negatively to the putative hereditary histories, and correctly responded negatively to empirically elevated colon cancer risk situations. This capability facilitates patient selection for DNA studies in search of gene mutations. When genetic mutations are included as parameters in a patient database for a genetic disease, the process yields an expert system which characterizes variations in clinical disease presentations in terms of genetic mutations. Such information can greatly improve the efficiency of gene testing.

Adult↗
PubMed1992

The role of automated speech recognition in endoscopic data collection.

Speech recognition technology has developed substantially in the past half decade. Currently, large vocabulary, speaker independent, discrete recognizers are the state-of-the-art. This will change. Moderate sized, continuous recognition systems now exist in research settings. However, it is unlikely that such systems will be widely available until the mid to late 1990's. The accuracy rates of current speech recognition systems are high. Consequently, speech accuracy is not the current limiting aspect of using ASR. The limiting aspect of using ASR technology is the approach to integrating speech functionality into applications. One approach is to use ATNs as models of natural language to support both an input strategy and a text generation system. ATNs provide approaches to both syntactical correctness and semantic richness. This is an approach which plays to the strengths of the discrete nature of current speech technology and also provides a methodology for the capture and archiving of highly detailed information. The ATN approach avoids the natural language parsing problem created by a fully free form dictation interface. Evolving along with the underlying speech technology are standards in the definitions and criteria used in endoscopic practice. There are clear benefits from standards in this area. However, it is likely that this will also take several years and may never yield a universally accepted lexicon. Furthermore, there will be user interface barriers to surmount in any system attempting to use speech as an input modality. Because of the relatively large vocabularies used in medical discourse, the user interface will need to be carefully crafted.(ABSTRACT TRUNCATED AT 250 WORDS)

Data Collection↗
PubMed1979

Detection of suspicious cells and rejection of artefacts in cervical cytology using the Leyden Television Analysis System.

In slide based automation of cervical cytology the first stage of analysis involves finding possibly suspicious cells, or areas on the slide with these types of cells. By using a television based system such as the Leyden Television Analysis System (LEYTAS), a number of detection methods can be applied to rapidly screen a large number of fields automatically for suspicious cells. In this paper, results using a parameter based on increased nuclear DNA content of cells are given and a second detection method based on a chromatin pattern feature, called chromatin contrast, is discussed. Two blind trials on 41 positive and 22 negative cervical slides, using the Leyden Television Analysis System to detect suspicious cells with an increased nuclear DNA content, were promising. In 1 of the 41 positive cases no suspicious cells were found. In the negative specimens, suspicious cells were detected in 1 of 9 cases and 1 of 13 cases, with the two detection parameters investigated. These findings are discussed and some automatic artefact rejection procedures with preliminary results are given.

Cervix Uteri↗
PubMed1995

An automated computer vision and robotics-based technique for 3-D flexible biomolecular docking and matching.

The generation of binding modes between two molecules, also known as molecular docking, is a key problem in rational drug design and biomolecular recognition. Docking a ligand, e.g., a drug molecule or a protein molecule, to a protein receptor, involves recognition of molecular surfaces as molecules interact at their surface. Recent studies report that the activity of many molecules induces conformational transitions by 'hinge-bending', which involves movements of relatively rigid parts with respect to each other. In ligand-receptor binding, relative rotational movements of molecular substructures about their common hinges have been observed. For automatically predicting flexible molecular interactions, we adapt a new technique developed in Computer Vision and Robotics for the efficient recognition of partially occluded articulated objects. These type of objects consist of rigid parts which are connected by rotary joints (hinges). Our approach is based on an extension and generalization of the Geometric Hashing and Generalized Hough Transform paradigm for rigid object recognition. Unlike other techniques which match each part individually, our approach exploits forcefully and efficiently enough the fact that the different rigid parts do belong to the same flexible molecule. We show experimental results obtained by an implementation of the algorithm for rigid and flexible docking. While the 'correct', crystal-bound complex is obtained with a small RMSD, additional, predictive 'high scoring' binding modes are generated as well. The diverse applications and implications of this general, powerful tool are discussed.

Algorithms↗
PubMed1994

Learning synergy in a multilevel neuronal architecture.

An artificial worlds model of the brain has been developed that integrates memory, intraneuronal dynamics and multilevel evolutionary learning. The model includes two major subsystems. The first is a memory-manipulation scheme, called the reference neuron system, that serves to orchestrate a repertoire of neurons with different input-output capabilities. Signals impinging on these neurons are integrated by a cytoskeletal structure that is simulated as a cellular automation. The second subsystem is an evolutionary learning scheme, called the selection circuits system, that serves to train the neurons in the repertoire by varying the cytoskeletal proteins that control signal flow or readouts. The integrated system comprises two layers of cytoskeletally controlled neurons and two layers of reference neurons. Evolution can occur at the level of readout enzymes in neurons, at the level of proteins that control the flow of signals in the cytoskeleton and at the level of reference neurons that orchestrate the repertoire. The integrated system controls the motion of a modeled organism that is embedded in an artificial environment consisting of barriers, food and a target. The organism effectively learns to use patterns of barriers in its local environment to find the target, using food as a reward. Experiments with the model show that the integrated system enjoys significant computational synergies that make it more powerful than the component systems standing alone, that interactions between different levels at which variation can occur exert significant control over the tempo of evolution, that the synergies between different components and levels becomes more important as the environment becomes more complex and that mutation strategies that significantly slow down the rate of learning significantly decrease the degrading effects of environmental noise on performance.

Biological Evolution↗
PubMed1995

A polygon matching algorithm and its applications to verification of radiation field placement in radiotherapy.

An automated method for quantitative evaluation of geometric accuracy of radiation field placement during radiation therapy treatments has been developed and is presented in this article. The method is based on matching polygons representing the boundaries of the prescribed and treated radiation fields. An efficient algorithm for finding the intersection of two arbitrary simple polygons has been developed for that purpose. The process of polygon matching is performed by iterative optimization of the goodness-of-match measure derived from the area of the intersection between the two polygons to be matched. The optimization is done with respect to the translation and rotation in the plane that are applied to the polygon representing the treated field. The optimum translation and rotation define the adjustments in the position of the treated field, relative to the patients anatomy, which are necessary in order to bring the treated field into the best possible agreement with the prescription. The radiation field matching scheme was applied to a clinical dataset consisting of prescription-treatment field pairs extracted from simulation and portal images for 40 patients. It is concluded that the observed accuracy and efficiency of the method make it very suitable for applications in radiation therapy verification.

Algorithms↗
PubMed1981

Within-day physiologic variation of leukocyte types in healthy subjects as assayed by two automated leukocyte differential analyzers.

The physiologic within-day (700-2200 h) variation of leukocyte-type concentrations in blood as determined for 21 healthy young adults is reported. All blood specimens were obtained in duplicate such that the within-batch analytic variation, as well as the pertinent biologic sources of variation, was able to be determined. All specimens were analyzed on each of two automated leukocyte differential systems: Hemalog-D Differential System and the Hematrak-240 Analyzer. On the basis of a comparison of the performances of the two analyzers, it was decided to report the neutrophil and the lymphocyte values as measured on both systems, the monocyte values as measured on teh Hematrak only, and the eosinophil and basophil values as measured on the Hemalog-D only. The intrasubject within-day physiologic variations for the cell on the Hemalog-D and Hematrak, respectively, in terms of coefficient of variation wee as follows: neutrophils 19.4% and 19.6%; lymphocytes, 13.8% and 17.5%. For monocytes, as measured on the Hematrak, it was 13.4%. For eosinophils and basophils, as measured on the Hemalog-D, it was 27.2% and 8.3%, respectively. There was a consistent group-specific diurnal variance that amounted to more than 40% of the total within-day variance, both for lymphocytes and for eosinophils. The within-day physiologic variation of the cell type concentrations for eight of the volunteers was compared with that of the plasma cortisol concentrations, as determined on specimens derived from the same veni-puncture sessions. The decrease in plasma cortisol values was in most instances associated with decreases in eosinophils and increases in neutrophils. For total leukocytes and neutrophils, the mean concentration for smokers was significantly higher than that for nonsmokers.

Adult↗
PubMed1997

A comparison of the accuracy and reproducibility of digital three-dimensional coronary artery reconstructions using edge detection or videodensitometry.

Global quantitative three-dimensional measurements of coronary arteries may be helpful in determining the functional significance of various forms of coronary pathology. A computerized system has been developed that is capable of performing 3-D reconstruction of digitized images obtained from multiple coronary angiographic views using either automated edge detection (AED) or videodensitometric (VD) techniques. To compare the accuracy and reproducibility of measurements obtained from this system using either technique, stationary and moving coronary aluminum 3-D phantoms, each with 13 branches (diameter 0.58-6.35 mm, length 21.5-64.5 mm), were imaged and reconstructed 10 separate times each. Individual branch lengths and diameters were calculated and compared to each other and to known values. Diameter measurements were compared using either AED or VD. Intraclass correlation coefficients between observed values (ICC) for vessel length were r = 0.89 for the stationary and r = 0.97 for the moving phantom. ICCs for vessel diameter were r = 0.93 (AED) and r = 0.95 (VD) for the stationary and r = 0.98 (AED) and r = 0.97 (VD) for the moving phantom. Mean differences (+/-SD) between true and observed values [MDTO(+/-SD)] for vessel length were -1.0 +/- 3.9 mm for the stationary and -3.5 +/- 3.2 mm for the moving phantom. MDTO(+/-SD) for vessel diameter were -0.10 +/- 0.52 mm (AED) and +0.03 +/- 0.30 mm (VD) for the stationary and -0.21 +/- 0. 44 mm (AED) and -0.12 +/- 0.33 (VD) for the moving phantom. We conclude that the quantitative accuracy and reproducibility of measurements obtained by computerized 3-D reconstruction of coronary model phantoms is of high enough quality to warrant further clinical evaluation. VD appears to be more accurate than AED for measuring vessel diameter.

Aluminum↗
PubMed1996

Morphometric analysis in three-dimensional intracoronary ultrasound: an in vitro and in vivo study performed with a novel system for the contour detection of lumen and plaque.

Currently, automated systems for quantitative analysis by intracoronary ultrasound (ICUS) are restricted to the detection of the lumen. The aim of this study was to determine the accuracy and reproducibility of a new semiautomated contour detection method, providing off-line identification of the intimal leading edge and external contour of the vessel in three-dimensional ICUS. The system allows cross-sectional and volumetric quantification of lumen and of plaque. It applies a minimum-cost algorithm and the concept that edge points derived from previously detected longitudinal contours guide and facilitate the contour detection in the cross-sectional images. A tubular phantom with segments of various luminal dimensions was examined in vitro during five catheter pull-backs (1 mm/sec), and subsequently 20 diseased human coronary arteries were studied in vivo with 2.9F 30 MHz mechanical ultrasound catheters (200 images per 20 mm segment). The ICUS measurements of phantom lumen area and volume revealed a high correlation with the true phantom areas and volumes (r = 0.99); relative mean differences were -0.65% to 3.86% for the areas and 0.25% to 1.72% for the volumes of the various segments. Intraob-server and interobserver comparisons showed high correlations (r = 0.95 to 0.98 for area and r = 0.99 for volume) and small mean relative differences (-0.87% to 1.08%), with SD of lumen, plaque, and total vessel measurements not exceeding 7.28%, 10.81%, and 4.44% (area) and 2.66%, 2.81%, and 0.67% (volume), respectively. Thus the proposed analysis system provided accurate measurements of phantom dimensions and can be used to perform highly reproducible area and volume measurements in three-dimensional ICUS in vivo.

Algorithms↗
PubMed1979

Differentiating exogenous psychiatric illness from schizophrenia.

Retaining an individual on psychiatric dispensary lists long after a single psychotic episode can result in unnecessary restriction of his or her social-vocational rights and responsibilities. This study demonstrates that an early clinical differention can be made between exogenous psychoses and progressive schizophrenia. The validity of the clinical differentiation was enhanced by demonstrating that a computer learning and pattern-recognition program was capable of using signs and symptoms recorded in the first psychotic episode to make a differential diagnosis that coincided closely with diagnoses made at a later date by clinicians aware of the subsequent clinical course. This kind of approach to standardized nosologic principles may expand the possibility for more appropriate application of psychotropic medications, psychotherapy, and somatic treatments, as well as more accurate social-vocational prognoses.

Acute Disease↗
PubMed1987

Use of pattern analysis to identify true drug response. A replication.

In any antidepressant study, placebo response in patients assigned active drug is a troubling source of variance. There have been few attempts to identify the patients whose conditions improve as a result of true drug effect, in contrast with improvement that is a result of nonspecific effects. In a previous report we demonstrated that true drug effect seemed to be characterized by a two-week delay in onset and persistence. We described a method of pattern analysis to identify such patients. In this report, we describe the use of pattern analysis to replicate our initial findings. Data from a new sample of 150 nonmelancholic patients support the hypothesis that true drug effect is characterized by a two-week delay in onset and persistence of improvement, once achieved. There was little evidence of the onset of antidepressant effect before two weeks. The theoretical and clinical implications of this work are discussed.

Actuarial Analysis↗