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 55 records · Page 3Linked to original sources
PubMed1995

Arthritis diagnosis based upon the near-infrared spectrum of synovial fluid.

Synovial fluid aspirates have been characterized by measuring their visible/near-infrared spectra (400-2500 nm). The hypothesis tested in this study is that the spectra contain sufficient information to serve as an aid in the diagnosis and/or staging of arthritic disorders. The concentrations of all major constituents are carried implicitly in the spectra, and in this sense this approach is similar in spirit to conventional synovial fluid analysis. The distinguishing feature of this method is that we have not converted the raw data (spectra) explicitly to analytical information. Rather, we have used automated pattern recognition methods to identify significant characteristics of the spectra themselves. A total of 109 spectra were measured and split into three classes according to the disease (osteoarthritis, rheumatoid arthritis, or spondyloarthropathy) affecting the patient from whom the synovial fluid sample was taken. An automated classification method was then trained by correlating features derived from these spectra to the clinical diagnoses. The robustness of the classification was validated using the leave-one-out cross-validation method, i.e., by training on all but one of the spectra and using the resulting model to predict the classification for the spectrum that is left out. The result derived by following this procedure for each of the spectra was that 105 of the 109 predicted classifications correctly matched the clinical diagnosis. These results suggest that the near-infrared spectrum of synovial fluid is sufficient to allow diagnosis of the disease affecting the joint from which the aspirate is drawn.

Arthritis, Rheumatoid↗
PubMed1997

Computer-assisted reading of mammograms.

Techniques developed in computer vision and automated pattern recognition can be applied to assist radiologists in reading mammograms. With the introduction of direct digital mammography this will become a feasible approach. A radiologist in breast cancer screening can use findings of the computer as a second opinion, or as a pointer to suspicious regions. This may increase the sensitivity and specificity of screening programs, and it may avoid the need for double reading. In this paper methods which have been developed for automated detection of mammographic abnormalities are reviewed. Programs for detecting microcalcification clusters and stellate lesions have reached a level of performance which makes application in practice viable. Current programs for recognition of masses and asymmetry perform less well. Large-scale studies still have to demonstrate if radiologists in a screening situation can deal with the relatively large number of false positives which are marked by computer programs, where the number of normal cases is much higher than in observer experiments conducted thus far.

Breast Neoplasms↗
PubMed1998

Detection of endotracheal tube obstruction by analysis of the expiratory flow signal.

OBJECTIVE: Acute obstruction of endotracheal tubes (ETT) increases airway pressure, decreases tidal volume, increases the risk of dynamic hyperinflation by prolonging the duration of passive expiration, and prevents reliable calculation of tracheal pressure. We propose a computer-assisted method for detecting ETT obstruction during controlled mechanical ventilation. The method only requires measurement of the expiratory flow. DESIGN: Computer simulation; prospective study in two cases; retrospective study in one case and in seven patients with the adult respiratory distress syndrome (ARDS). SETTING: Laboratory of the Section of Experimental Anaesthesiology (University of Freiburg); surgical adult intensive care units in a university hospital (University of Basel) and in a university affiliated hospital (Zentralklinikum Augsburg). PATIENTS: 3 patients with partial ETT or bronchial obstructions and 7 ARDS patients. MEASUREMENTS AND RESULTS: Expiratory flow was measured using a pneumotachograph and integrated to obtain expiratory volume. The time-constant of passive expiration (tauE) as a function of expired volume [tauE(V(E)) function] was calculated from the expiratory volume/flow curve. We investigated the tauE(V(E)) function of data obtained from: (1) computer simulation of mechanically ventilated homogeneous and inhomogeneous lungs intubated with ETTs of different sizes; (2) one patient with an artificial ETT obstruction of 7.5 and 25% of the cross-sectional area of the ETT (case 1); (3) one patient with ETT obstruction due to secretions (case 2); (4) one patient with acute bronchial constriction (case 3); (5) seven ARDS patients who showed an increase in airway resistance of more than 2 cm H2O x s/l. It was found that an ETT obstruction caused an increase in tauE in early expiration (at high flow), whereas tauE in late expiration was virtually unchanged. The reason for this is the flow dependency of the increase in ETT resistance produced by ETT obstruction. Unlike ETT obstruction, an increase in pure airway resistance produced an increase in tauE throughout expiration. CONCLUSIONS: An ETT obstruction can be reliably distinguished from an increase in pure airway resistance by a characteristic pattern change in the tauE(V(E)) function, which can be detected easily even by an automated pattern recognition system.

Aged↗
PubMed1998

Detection of lung injury with conventional and neural network-based analysis of continuous data.

OBJECTIVE: To test if analysis of pressure and flow waveform patterns with an artificial intelligence neural network could distinguish between normal and injured lungs. METHODS: Acute lung injury was induced in ten healthy anesthetized, mechanically ventilated dogs with repeated injections of oleic acid, until arterial blood oxyhemoglobin saturation reached 85% breathing room air. Airway pressure, esophageal pressure, airway flow, and arterial and mixed venous saturation signals were stored at 2 min intervals. Hemodynamic and blood gas data were collected every 10 min. Back-propagation neural networks were trained with normalized airway pressure and flow waveforms from normal and fully injured lungs. RESULTS: The networks scored lung injury on a continuous scale from +1 (normal) to -1 (injured). Network scores unequivocally distinguished between normal and fully injured lungs and suggested a gradual transition from normal to injury pattern. However, the response of the network was slow compared to compliance, resistance and venous admixture. CONCLUSIONS: Normal and fully injured lungs display distinct flow and pressure waveform patterns which are independent of changes in calculated pulmonary mechanics variables. These patterns can be recognized by a neural network. Further research is needed to determine the full potential of automated pattern recognition for lung monitoring.

Animals↗
PubMed1977

[A new image-processing system designed for densitometry and pattern analysis of microscopic specimen. Application to the automated recognition and counting of cells in the various phases of the mitotic cycle (author's transl)].

A new image analysing system, designed for microphotometric measurement and pattern recognition has been applied in the discrimination of cells from the various phases of the mitotic cycle. The data acquisition procedure is controlled by a programmable electronic unit and involves the combination of the shifting of the microscope moving stages and the scanning of the successive fields by a mechanical device. The data processing is achieved by a computer. The preliminary results we obtained have shown that such a system allows the automatic recognition and counting of the M, G1, S and G2 cells as also the G0 resting cells. The most useful parameters of the cell proliferation kinetics are thus obtained from a single specimen of a cell population.

Cell Count↗
PubMed1997

What do we know about how dentists make caries-related treatment decisions?

A conceptual model of dentists' treatment decision-making is discussed. The model suggests that dentists do not use a hypothetico-deductive process for the diagnosis of caries. Rather, caries is identified through a process of pattern recognition that in most instances is inextricably linked to intervention decisions. Individual dentists have inventories of caries scripts that, when matched by a particular clinical presentation, lead to decisions to treat. The scripts comprise salient factors that are dependent on individual dentist's characteristics and biases, and thus vary substantially across dentists. The scripts tend to be complex, highly visual, and difficult to describe. All of these characteristics suggest that efforts to improve dentists' caries-related treatment decisions should acknowledge this knowledge structure and be designed to change the salient factors or interpretations of salient factors within the context of the caries script.

Attitude of Health Personnel↗
PubMed1984

Detection of abnormal cells in white cell differentials: comparison of the HEMATRAK automated system with manual methods.

Automated differential systems can rapidly count larger numbers of cells compared with the standard manual procedure. When a fixed number of abnormal cells are interspersed randomly with a large number of normal cells, it can be shown mathematically that counting more cells increases the chances of detecting at least one abnormal cell. To test this hypothesis in a clinical setting, the authors compared 200-cell and 400-cell automated differentials obtained via the HEMATRAK Model 360 system with results of 100-cell differentials performed either manually or automatically for a group of 141 blood smears. Manual 100-cell differentials also were performed in a reference laboratory for comparison. In close agreement with theoretical expectation, both 200-cell and 400-cell differentials detected significantly more abnormal cells than did either the manual or automated 100-cell differential. Results of the latter two were not significantly different. Eighty-seven per cent of the slides that, according to the 100-cell manual differential, were without abnormal cells were found to have such cells on the 400-cell automated differential. Atypical lymphocytes and nucleated red blood cells were the abnormal cells most frequently identified.

Automation↗
PubMed2001

SALSA: a pattern recognition algorithm to detect electrophile-adducted peptides by automated evaluation of CID spectra in LC-MS-MS analyses.

A pattern recognition algorithm called SALSA (scoring algorithm for spectral analysis) has been developed to rapidly screen large numbers of peptide MS-MS spectra for fragmentation characteristics indicative of specific peptide modifications. The algorithm facilitates sensitive and specific detection of modified peptides at low abundance in an enzymatic protein digest. SALSA can simultaneously score multiple user-specified search criteria, including product ions, neutral losses, charged losses, and ion pairs that are diagnostic of specific peptide modifications. Application of SALSA to the detection of peptide adducts of the electrophiles dehydromonocrotaline, benzoquinone, and iodoacetic acid permitted their detection in a complex tryptic peptide digest mixture. SALSA provides superior detection of adducted peptides compared to conventional tandem MS precursor ion or neutral loss scans.

Algorithms↗
PubMed2002

Temporal classification of Drosophila segmentation gene expression patterns by the multi-valued neural recognition method.

In order to reconstruct the establishment of the body pattern over time in Drosophila embryos, we have developed automated methods for detecting the age of an embryo on the basis of knowledge about its gene expression patterns. In this paper we perform temporal classification of confocal images of expression patterns of genes controlling segmentation by means of a neural network based on multi-valued neurons (MVN). MVN are artificial neural processing elements with complex-valued weights and high functionality, which proved to be efficient for solving the image recognition problems. The results obtained by this method confirm its efficiency for image recognition and indicate that the method can detect characteristic features of expression patterns which mark their development over time.

Animals↗
PubMed2000

Determining protein structure from electron-density maps using pattern matching.

TEXTAL is an automated system for building protein structures from electron-density maps. It uses pattern recognition to select regions in a database of previously determined structures that are similar to regions in a map of unknown structure. Rotation-invariant numerical values, called features, of the electron density are extracted from spherical regions in an unknown map and compared with features extracted around regions in maps generated from a database of known structures. Those regions in the database that match best provide the local coordinates of atoms and these are accumulated to form a model of the unknown structure. Similarity between the regions in the database and an uninterpreted region is determined firstly by evaluating the numerical difference in feature values and secondly by calculating the electron-density correlation coefficient for those regions with similar feature values. TEXTAL has been successful at building protein structures for a wide range of test electron-density maps and can automatically model entire protein structures in a few hours on a workstation. Models built by TEXTAL from test electron-density maps of known protein structures were accurate to within 0.6-0.7 A root-mean-square deviation, assuming prior knowledge of C(alpha) positions. The system represents a new approach to protein structure determination and has the potential to greatly reduce the time required to interpret electron-density maps in order to build accurate protein models.

Algorithms↗
PubMed1995

Speech technology in 2001: new research directions.

Research in speech recognition and synthesis over the past several decades has brought speech technology to a point where it is being used in "real-world" applications. However, despite the progress, the perception remains that the current technology is not flexible enough to allow easy voice communication with machines. The focus of speech research is now on producing systems that are accurate and robust but that do not impose unnecessary constraints on the user. This chapter takes a critical look at the shortcomings of the current speech recognition and synthesis algorithms, discusses the technical challenges facing research, and examines the new directions that research in speech recognition and synthesis must take in order to form the basis of new solutions suitable for supporting a wide range of applications.

Automation↗
PubMed1988

Automated classification of periodontal disease using bitewing radiographs.

The feasibility of applying a prototype, computer-based pattern recognition system to the objective classification of periodontal disease using dental radiographs was tested. Twenty-nine observer-classified bitewing radiographs, representing seven individuals with varying grades of periodontal disease, were selected. The radiographs were digitized using a computer-controlled TV camera. Mathematical features of these radiographs were interactively extracted using a digital image processing system (International Imaging Systems Model 75 and System/575). The features extracted from these radiographs included the brightness levels of cortical and trabecular bone and ratios of bone-loss to linear-crown height. Twenty-eight mathematically defined features (variables) were determined for each radiograph. Stepwise linear discriminant analysis used these features to classify subjects based on the presence and extent of periodontal disease. This pattern recognition system was able to grade periodontal disease in our test series with percentages of correct classifications ranging from 78.8% to 91%. This technology is particularly applicable to the development of morbidity and activity indices for periodontal diseases.

Alveolar Process↗