[Automated pattern recognition of clinical electroencephalogram (author's transl)].
Explore the source record for details and available documents.
Computers↗
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.
Polysomnographic pattern recognition for automated classification of sleep-waking states in infants.
A robust, automated pattern recognition system for polysomnography data targeted to the sleep-waking state and stage identification is presented. Five patterns were searched for: slow-delta and theta wave predominance in the background electro-encephalogram (EEG) activity; presence of sleep spindles in the EEG; presence of rapid eye movements in an electro-oculogram; and presence of muscle tone in an electromyogram. The performance of the automated system was measured indirectly by evaluating sleep staging, based on the experts' accepted methodology, to relate the detected patterns in infants over four months of post-term age. The set of sleep-waking classes included wakefulness, REM sleep and non-REM sleep stages I, II, and III-IV. Several noise and artifact rejection methods were implemented, including filters, fuzzy quality indices, windows of variable sizes and detectors of limb movements and wakefulness. Eleven polysomnographic recordings of healthy infants were studied. The ages of the subjects ranged from 6 to 13 months old. Six recordings counting 2665 epochs were included in the training set. Results on a test set (2,369 epochs from five recordings) show an overall agreement of 87.7% (kappa 0.840) between the automated system and the human expert. These results show significant improvements compared with previous work.
Algorithms↗
Automated recognition of patterns characteristic of subcellular structures in fluorescence microscopy images.
Methods for numerical description and subsequent classification of cellular protein localization patterns are described. Images representing the localization patterns of 4 proteins and DNA were obtained using fluorescence microscopy and divided into distinct training and test sets. The images were processed to remove out-of-focus and background fluorescence and 2 sets of numeric features were generated: Zernike moments and Haralick texture features. These feature sets were used as inputs to either a classification tree or a neural network. Classifier performance (the average percent of each type of image correctly classified) on previously unseen images ranged from 63% for a classification tree using Zernike moments to 88% for a backpropagation neural network using a combination of features from the 2 feature sets. These results demonstrate the feasibility of applying pattern recognition methods to subcellular localization patterns, enabling sets of previously unseen images from a single class to be classified with an expected accuracy greater than 99%. This will provide not only a new automated way to describe proteins, based on localization rather than sequence, but also has potential application in the automation of microscope functions and in the field of gene discovery.
Image Enhancement↗
Standardization of dyes and stains for automated cell pattern recognition.
An extensive review is presented of the various factors involved in the standardization of dyes and stains for cytologic material, which is a crucial point in achieving objective and reproducible measurements of cells for recognition by automated microscopy (high-resolution cell image analysis; automated cell pattern recognition [ACPR]). Two principal methods of standardization are considered at length: (1) standardization based on the physical and chemical characterization of the dyes (physicochemical standardization), as adopted by the German Bureau of Standards, and (2) standardization based on direct visual assessment of stain performance (performance standardization), as adopted by the United States Biological Stain Commission. The procedures, achievements and problems of both methodologies are discussed, as are such related matters as staining time, solution pH, etc., especially with regard to the two most important stains in diagnostic cytology: the Papanicolaou stain and the Romanowsky-Giemsa stain. The standardization of these two stains is considered in detail, with an eye towards their suitability for ACPR. The mechanisms of the staining results produced by these stains are examined, as are the extant problems with each. The Papanicolaou stain, while neither standardized nor stoichiometric, has proven to be of use in cytophotometry. Similarly, the Romanowsky-Giemsa stain, while standardized, is also not a stoichiometric stain. Yet both have been successfully used in some aspects of ACPR; no "ideal" stain has yet been found that would make cell samples ideally suited for machine evaluation. It is concluded that the standardization of biologic dyes and stains, which can contribute to the success of ACPR, should be undertaken by multidisciplinary expert panels, in which the current concerned organizations could play a role. It is also concluded that ACPR may, in fact, contribute to the standardization of dyes and stains: that computer-directed morphometry and automated image analysis with sophisticated statistical analysis may become major tools in the validation of data on staining. For example, computer analysis could be used to pinpoint the particular variant of the Papanicolaou stain that leads to the best overall reproducibility of cell descriptors, in effect achieving "preliminary standardization by computer judgment of stain performance."
Adjuvants, Pharmaceutic↗
The automated differential; pattern recognition systems, precision, and the spun smear.
Utilizing normal patient blood samples, two automated differential pattern recognition systems, the ADC-500 and the Hematrak 360, were compared in a duplicate study with the manual eye method, using spun and wedge smear preparations. The study showed a superior precision for the 500-cell differential, but occasional data points with spun smears were unusually drifted from the central cluster for both the manual and instrument methods. Analysis of the data uncovered at least two reasons for these unusual outliers: "star artifacts" and warped glass slides. The importrance of these method-related artifacts are discussed, alo ng with the future of the 500-cell differential with today's automated technology.
Autoanalysis↗
Computer pattern recognition: an automated method for evaluating motor activity and testing for neurotoxicity.
An economical computer-based pattern recognition system, which has been designed to observe, classify, analyze, and record the spontaneous motor activity of the laboratory rat, is presented. The advantages and disadvantages of the system are assessed in terms of characteristics generally held to be desirable for a motor activity screen of potentially neurotoxic chemicals. Data from rats exposed to 1 mg/kg d-amphetamine are compared with similar data previously taken with an earlier version of the system at another laboratory.
Animals↗
Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study.
Automated pattern recognition techniques are needed to help radiologists categorize MRS data of brain tumors according to histological type and grade. A major question is whether a computer program "trained" on spectra from one hospital will be able to classify those from another, particularly if the acquisition protocol is different. A subset of 144 histopathologically validated brain tumor spectra in the INTERPRET database, obtained from three of the collaborating centers, was grouped into meningiomas, low-grade astrocytomas, and "aggressive tumors" (glioblastomas and metastases). Spectra from two centers formed the training set (94 spectra) while the third acted as the test set (50 spectra). Linear discriminant analysis successfully classified 48/50 in the test set; the remaining two were atypical cases. When the training and test sets were combined, 133 of the 144 spectra were correctly classified using the leave-one-out procedure. These spectra had been obtained using different sequences (STEAM and PRESS), different echo times (20, 30, 31, and 32 ms), different repetition times (1600 and 2000 ms), and different manufacturers' instruments (GE and Philips). Pattern recognition algorithms are less sensitive to acquisition parameters than had been expected.
Astrocytoma↗
Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra.
A computer-based decision support system to assist radiologists in diagnosing and grading brain tumours has been developed by the multi-centre INTERPRET project. Spectra from a database of 1H single-voxel spectra of different types of brain tumours, acquired in vivo from 334 patients at four different centres, are clustered according to their pathology, using automated pattern recognition techniques and the results are presented as a two-dimensional scatterplot using an intuitive graphical user interface (GUI). Formal quality control procedures were performed to standardize the performance of the instruments and check each spectrum, and teams of expert neuroradiologists, neurosurgeons, neurologists and neuropathologists clinically validated each case. The prototype decision support system (DSS) successfully classified 89% of the cases in an independent test set of 91 cases of the most frequent tumour types (meningiomas, low-grade gliomas and high-grade malignant tumours--glioblastomas and metastases). It also helps to resolve diagnostic difficulty in borderline cases. When the prototype was tested by radiologists and other clinicians it was favourably received. Results of the preliminary clinical analysis of the added value of using the DSS for brain tumour diagnosis with MRS showed a small but significant improvement over MRI used alone. In the comparison of individual pathologies, PNETs were significantly better diagnosed with the DSS than with MRI alone.
Algorithms↗
Fuzzy sets for feature identification in biomedical signals with self-assessment of reliability: an adaptable algorithm modeling human procedure in BAEP analysis.
The analysis of biomedical signals has mostly been restricted to traditional signal-processing methods. This article proposes a different approach, applied to the evaluation of brainstem auditory evoked potentials. An automatic peak identification method is described which uses criteria applied by human evaluators in visual analysis. These criteria are defined as fuzzy sets and are combined using fuzzy operations, thus reflecting the weighting of different facts by humans. Membership values are interpreted as degrees of satisfaction which indicate the degree to which a sample satisfies a given criterion. The system judges its own performance in terms of degrees of reliability. Tests on a large set of clinical data showed high performance on good and average-quality curves. A substantial drawback was the assignment of too many peaks in poor potentials. The approaches presented here can easily be applied to similar one-dimensional (and higher) signal analysis tasks.
Algorithms↗
Cat and monkey cortical columnar patterns modeled by bandpass-filtered 2D white noise.
A simple algorithm based on bandpass-filtering of white noise images provides good quality computer reconstruction of the cat and monkey ocular dominance and orientation column patterns. A small number of parameters control the frequency, orientation, "branchedness", and "regularity" of the column patterns. An oriented (anisotropic) bandpass filter followed by a threshold operation models the macaque ocular dominance column pattern and cat orientation column system. An unoriented (isotropic) bandpass filter models the cat ocular dominance column pattern and the macaque orientation column system. The resemblance of computer graphic simulations produced by this algorithm and histological pattern data, is strong. Since this algorithm is very fast, we have been able to extensively explore its parameters space in order to determine filter parameters which closely match the structure of the various cortical systems. In particular, we have applied spectral analysis to our recent computer reconstruction of the macaque ocular dominance column system, and the model produced by the present algorithm is in close agreement with this detailed data analysis.
Algorithms↗
Recognition of hierarchically encoded images by technical and biological systems.
All the contours and regions of objects can be mapped to code-trees of the Hierarchical Structure Code (HSC). Invariant features like structure classes, shape descriptions, or relations between structures and components may be easily extracted from the HSC. HSC-based pattern recognition provides a straightforward transition between the signal-space of the image and the space of its symbolic representation. Physiological data are well predicted and do not exclude an implementation of an HSC-based system within the visual cortex.
Cybernetics↗
On the recognition of order and disorder.
We compare several algorithms for the recognition of ordered and disordered images. As image sources we use waves of the Belousov-Zhabotinskii reaction coupled to convective motion in a petri dish. This device allows reversibly the generation of periodic (ordered) and aperiodic (disordered) patterns. The best match between the parametric description and the observations is obtained by an "autodifference function". This function is computed by summing up intensity differences over all pairs of picture elements having a given distance on the picture plane. Then, the minimum of this function is determined upon variation of the distance. This algorithm is not only efficient for the recognition of order and disorder in "machine vision", but also plausible in biological visual perception.
Form Perception↗
A model of a human recognition system with 'thinking'.
The human system of pattern recognition is explored. This system utilizes the method of syntactic feature comparison, activation of the patterns containing the feature, and sorting among the activated patterns. Both the pattern recognition process without thinking and with thinking are discussed, and examples are given. Contrary to the usual concept, the more complicated pattern has a better chance to be recognized correctly.
Computers↗
Image enhancement for electronic visual prostheses.
This paper briefly describes the framework of artificial human vision systems and identifies several image processing techniques which could enhance the information content of artificially-induced images. We describe our own research in this area, which aims to assess the performance of proposed devices, specifically the usefulness of low quality images associated with electronic visual prostheses. Our subjective assessment studies using representative test patterns have investigated how much information and what types of information are needed to recognise or perceive a scene. 174 normally sighted subjects viewed a set of low quality (low spatial resolution and low grey-scale) static images. Results from this testing has identified informative image processing operations which lead to improved understanding of picture content.
Algorithms↗
Learning invariant object recognition in the visual system with continuous transformations.
The cerebral cortex utilizes spatiotemporal continuity in the world to help build invariant representations. In vision, these might be representations of objects. The temporal continuity typical of objects has been used in an associative learning rule with a short-term memory trace to help build invariant object representations. In this paper, we show that spatial continuity can also provide a basis for helping a system to self-organize invariant representations. We introduce a new learning paradigm "continuous transformation learning" which operates by mapping spatially similar input patterns to the same postsynaptic neurons in a competitive learning system. As the inputs move through the space of possible continuous transforms (e.g. translation, rotation, etc.), the active synapses are modified onto the set of postsynaptic neurons. Because other transforms of the same stimulus overlap with previously learned exemplars, a common set of postsynaptic neurons is activated by the new transforms, and learning of the new active inputs onto the same postsynaptic neurons is facilitated. We demonstrate that a hierarchical model of cortical processing in the ventral visual system can be trained with continuous transform learning, and highlight differences in the learning of invariant representations to those achieved by trace learning.
Computer Simulation↗
Enhancement of perceptually salient contours using a parallel artificial cortical network.
In this paper we present a parallel artificial cortical network inspired by the Human visual system, which enhances the salient contours of an image. The network consists of independent processing elements, which are organized into hypercolumns. They process concurrently the distinct orientations of all the edges of the image. These processing elements are a new set of orientation kernels appropriate for the discrete lattice of the hypercolumns. The Gestalt laws of proximity and continuity that describe the process of saliency extraction in the human brain are encoded by means of weights. These weights interconnect the kernels according to a novel connection pattern based on co-exponentiality. The output of every kernel is modulated by the outputs of its neighboring kernels, according to a new affinity function. This function takes into account the degree of difference between the facilitation of the two lobes of the kernel. Saliency enhancement results as a consequence of the local interactions between the kernels. The network was tested on real and synthetic images and displays promising results for both. Comparisons with other methods with the same scope, demonstrate that the proposed method performs adequately. Furthermore it exhibits O(N) complexity with execution times that have never been reported by any other method so far, even though it is executed on a conventional PC.
Artificial Intelligence↗
Machine recognition in pathology.
Explore the source record for details and available documents.
Diagnosis, Computer-Assisted↗
Efficiency of searchpatterns.
Search theory deals with the efficiency of covering searchpatterns; a classical example is systematic row search with sweep spacing dependent upon window size. Human visual search is a function of contrast and size of the targets and of effective visual lobe size, this latter influenced by clutter and foveal load. Human searchpatterns often are optimal covers. Experimental results presented in this paper demonstrate that this is true for instrumental search with display windows controlled by human subjects and quantified with a formula for efficiency. Visual searchpatterns using free eye movements often develop complex irregular sequential searchpatterns.
Humans↗