Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “CLASSIFICATION”

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 1,423 records · Page 79Linked to original sources
PubMed2005

A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques.

Ventricular tachyarrhythmias, in particular ventricular fibrillation (VF), are the primary arrhythmic events in the majority of patients suffering from sudden cardiac death. Attention has focused upon these articular rhythms as it is recognized that prompt therapy can lead to a successful outcome. There has been considerable interest in analysis of the surface electrocardiogram (ECG) in VF centred on attempts to understand the pathophysiological processes occurring in sudden cardiac death, predicting the efficacy of therapy, and guiding the use of alternative or adjunct therapies to improve resuscitation success rates. Atrial fibrillation (AF) and ventricular tachycardia (VT) are other types of tachyarrhythmias that constitute a medical challenge. In this paper, a high order spectral analysis technique is suggested for quantitative analysis and classification of cardiac arrhythmias. The algorithm is based upon bispectral analysis techniques. The bispectrum is estimated using an autoregressive model, and the frequency support of the bispectrum is extracted as a quantitative measure to classify atrial and ventricular tachyarrhythmias. Results show a significant difference in the parameter values for different arrhythmias. Moreover, the bicoherency spectrum shows different bicoherency values for normal and tachycardia patients. In particular, the bicoherency indicates that phase coupling decreases as arrhythmia kicks in. The simplicity of the classification parameter and the obtained specificity and sensitivity of the classification scheme reveal the importance of higher order spectral analysis in the classification of life threatening arrhythmias. Further investigations and modification of the classification scheme could inherently improve the results of this technique and predict the instant of arrhythmia change.

Algorithms↗
PubMed2005

A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses.

This paper introduces and evaluates the use of Gaussian mixture models (GMMs) for multiple limb motion classification using continuous myoelectric signals. The focus of this work is to optimize the configuration of this classification scheme. To that end, a complete experimental evaluation of this system is conducted on a 12 subject database. The experiments examine the GMMs algorithmic issues including the model order selection and variance limiting, the segmentation of the data, and various feature sets including time-domain features and autoregressive features. The benefits of postprocessing the results using a majority vote rule are demonstrated. The performance of the GMM is compared to three commonly used classifiers: a linear discriminant analysis, a linear perceptron network, and a multilayer perceptron neural network. The GMM-based limb motion classification system demonstrates exceptional classification accuracy and results in a robust method of motion classification with low computational load.

Algorithms↗
PubMed2006

Surface myoelectric signal analysis: dynamic approaches for change detection and classification.

Toward the goal of elbow and wrist prostheses control by characterizing events in surface myoelectric signals, this paper presents a dynamic method to simultaneously detect and classify such events. Dynamic cumulative sum of local generalized likelihood ratios using wavelet decomposition of the myoelectric signal is used for on-line detection. Frequency as well as energy changes are detected with this hybrid approach. Classification is composed of using multiresolution wavelet analysis and autoregressive modeling to extract signal features while polynomial classifiers are used for pattern modeling and matching. The results of detecting and classifying four elbow and wrist movements show that, in average, 91% of the events are correctly detected and classified using features obtained from multiresolution wavelet analysis while 95% accuracy is achieved with AR modeling. The classification accuracy decreases, however, if short prostheses response delay is desired. This paper also shows that the performance of the polynomial classifiers is better than that of the commonly used neural networks since it gives higher classification accuracy and consistent classification outcomes. In comparison to the well known support vector machine classification, the polynomial classifier gives similar results without the need to optimize and search for classifier parameters.

Action Potentials↗
PubMedDate not supplied

Three-dimensional shape-structure comparison method for protein classification.

In this paper, a 3D shape-based approach is presented for the efficient search, retrieval, and classification of protein molecules. The method relies primarily on the geometric 3D structure of the proteins, which is produced from the corresponding PDB files and secondarily on their primary and secondary structure. After proper positioning of the 3D structures, in terms of translation and scaling, the Spherical Trace Transform is applied to them so as to produce geometry-based descriptor vectors, which are completely rotation invariant and perfectly describe their 3D shape. Additionally, characteristic attributes of the primary and secondary structure of the protein molecules are extracted, forming attribute-based descriptor vectors. The descriptor vectors are weighted and an integrated descriptor vector is produced. Three classification methods are tested. A part of the FSSP/DALI database, which provides a structural classification of the proteins, is used as the ground truth in order to evaluate the classification accuracy of the proposed method. The experimental results show that the proposed method achieves more than 99 percent classification accuracy while remaining much simpler and faster than the DALI method.

Algorithms↗
PubMed2004

Embedded image compression based on wavelet pixel classification and sorting.

The method of modeling and ordering in wavelet domain is very important to design a successful algorithm of embedded image compression. In this paper, the modeling is limited to "pixel classification," the relationship between wavelet pixels in significance coding. Similarly, the ordering is limited to "pixel sorting," the coding order of wavelet pixels. We use pixel classification and sorting to provide a better understanding of previous works. The image pixels in wavelet domain are classified and sorted, either explicitly or implicitly, for embedded image compression. A new embedded image code is proposed based on a novel pixel classification and sorting (PCAS) scheme in wavelet domain. In PCAS, pixels to be coded are classified into several quantized contexts based on a large context template and sorted based on their estimated significance probabilities. The purpose of pixel classification is to exploit the intraband correlation in wavelet domain. Pixel sorting employs several fractional bit-plane coding passes to improve the rate-distortion performance. The proposed pixel classification and sorting technique is simple, yet effective, producing an embedded image code with excellent compression performance. In addition, our algorithm is able to provide either spatial or quality scalability with flexible complexity.

Algorithms↗
PubMed2003

Detection of spectral signatures in multispectral MR images for classification.

This paper presents a new spectral signature detection approach to magnetic resonance (MR) image classification. It is called constrained energy minimization (CEM) method, which is derived from the minimum variance distortionless response in passive sensor array processing. It considers a bank of spectral channels as an array of sensors where each spectral channel represents a sensor and object spectral signature in multispectral MR images are viewed as signals impinging upon the array. The strength of the CEM lies on its ability in detection of spectral signatures of interest without knowing image background. The detected spectral signatures are then used for classification. The CEM makes use of a finite impulse response (FIR) filter to linearly constrain a desired object while minimizing interfering effects caused by other unknown signal sources. Unlike most spatial-based classification techniques, the proposed CEM takes advantage of spectral characteristics to achieve object detection and classification. A series of experiments is conducted and compared with the commonly used c-means method for performance evaluation. The results show that the CEM method is a promising and effective spectral technique for MR image classification.

Algorithms↗
PubMed2005

Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images.

This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.

Adult↗
PubMed2005

Maximum-likelihood techniques for joint segmentation-classification of multispectral chromosome images.

Traditional chromosome imaging has been limited to grayscale images, but recently a 5-fluorophore combinatorial labeling technique (M-FISH) was developed wherein each class of chromosomes binds with a different combination of fluorophores. This results in a multispectral image, where each class of chromosomes has distinct spectral components. In this paper, we develop new methods for automatic chromosome identification by exploiting the multispectral information in M-FISH chromosome images and by jointly performing chromosome segmentation and classification. We (1) develop a maximum-likelihood hypothesis test that uses multispectral information, together with conventional criteria, to select the best segmentation possibility; (2) use this likelihood function to combine chromosome segmentation and classification into a robust chromosome identification system; and (3) show that the proposed likelihood function can also be used as a reliable indicator of errors in segmentation, errors in classification, and chromosome anomalies, which can be indicators of radiation damage, cancer, and a wide variety of inherited diseases. We show that the proposed multispectral joint segmentation-classification method outperforms past grayscale segmentation methods when decomposing touching chromosomes. We also show that it outperforms past M-FISH classification techniques that do not use segmentation information.

Algorithms↗
PubMed2003

Hierarchical learning architecture with automatic feature selection for multiclass protein fold classification.

The structure classification of proteins plays a very important role in bioinformatics, since the relationships and characteristics among those known proteins can be exploited to predict the structure of new proteins. The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications, the role of appropriate features has not been paid adequate importance. In this investigation we use three novel ideas for multiclass protein fold classification. First, we use the gating neural network, where each input node is associated with a gate. This network can select important features in an online manner when the learning goes on. At the beginning of the training, all gates are almost closed, i.e., no feature is allowed to enter the network. Through the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly, and some gates may be partially open. The second novel idea is to use a hierarchical learning architecture (HLA). The classifier in the first level of HLA classifies the protein features into four major classes: all alpha, all beta, alpha + beta, and alpha/beta. And in the next level we have another set of classifiers, which further classifies the protein features into 27 folds. The third novel idea is to induce the indirect coding features from the amino-acid composition sequence of proteins based on the N-gram concept. This provides us with more representative and discriminative new local features of protein sequences for multiclass protein fold classification. The proposed HLA with new indirect coding features increases the protein fold classification accuracy by about 12%. Moreover, the gating neural network is found to reduce the number of features drastically. Using only half of the original features selected by the gating neural network can reach comparable test accuracy as that using all the original features. The gating mechanism also helps us to get a better insight into the folding process of proteins. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it also reduces the computation time.

Algorithms↗
PubMed2005

Data classification with radial basis function networks based on a novel kernel density estimation algorithm.

This paper presents a novel learning algorithm for efficient construction of the radial basis function (RBF) networks that can deliver the same level of accuracy as the support vector machines (SVMs) in data classification applications. The proposed learning algorithm works by constructing one RBF subnetwork to approximate the probability density function of each class of objects in the training data set. With respect to algorithm design, the main distinction of the proposed learning algorithm is the novel kernel density estimation algorithm that features an average time complexity of O(n log n), where n is the number of samples in the training data set. One important advantage of the proposed learning algorithm, in comparison with the SVM, is that the proposed learning algorithm generally takes far less time to construct a data classifier with an optimized parameter setting. This feature is of significance for many contemporary applications, in particular, for those applications in which new objects are continuously added into an already large database. Another desirable feature of the proposed learning algorithm is that the RBF networks constructed are capable of carrying out data classification with more than two classes of objects in one single run. In other words, unlike with the SVM, there is no need to resort to mechanisms such as one-against-one or one-against-all for handling datasets with more than two classes of objects. The comparison with SVM is of particular interest, because it has been shown in a number of recent studies that SVM generally are able to deliver higher classification accuracy than the other existing data classification algorithms. As the proposed learning algorithm is instance-based, the data reduction issue is also addressed in this paper. One interesting observation in this regard is that, for all three data sets used in data reduction experiments, the number of training samples remaining after a naive data reduction mechanism is applied is quite close to the number of support vectors identified by the SVM software. This paper also compares the performance of the RBF networks constructed with the proposed learning algorithm and those constructed with a conventional cluster-based learning algorithm. The most interesting observation learned is that, with respect to data classification, the distributions of training samples near the boundaries between different classes of objects carry more crucial information than the distributions of samples in the inner parts of the clusters.

Algorithms↗
PubMedDate not supplied

An intelligent system approach to higher-dimensional classification of volume data.

In volume data visualization, the classification step is used to determine voxel visibility and is usually carried out through the interactive editing of a transfer function that defines a mapping between voxel value and color/opacity. This approach is limited by the difficulties in working effectively in the transfer function space beyond two dimensions. We present a new approach to the volume classification problem which couples machine learning and a painting metaphor to allow more sophisticated classification in an intuitive manner. The user works in the volume data space by directly painting on sample slices of the volume and the painted voxels are used in an iterative training process. The trained system can then classify the entire volume. Both classification and rendering can be hardware accelerated, providing immediate visual feedback as painting progresses. Such an intelligent system approach enables the user to perform classification in a much higher dimensional space without explicitly specifying the mapping for every dimension used. Furthermore, the trained system for one data set may be reused to classify other data sets with similar characteristics.

Algorithms↗
PubMed2006

Subtypes of substance dependence and abuse: implications for diagnostic classification and empirical research.

AIMS: To evaluate the relevance of a form of diagnostic classification called clinical subtyping in relation to possible revisions in the diagnostic criteria for substance abuse and dependence in psychiatric classification systems. METHODS: A general rationale for subtyping is presented. To explore the implications for diagnostic classification, recent research on a variety of subtyping schemes is reviewed in terms of the development of new subtypes and the validation of established theories. RESULTS: Subtypes of alcoholism and other psychiatric disorders have been proposed since the beginning of modern psychiatry. Recent subtyping research suggests that no consensus has emerged about the nature, much less the number, of subtypes that could be used to characterize the clinical heterogeneity assumed to be present in groups of people with substance use disorders. Although several relatively simple binary typologies have been developed (e.g. Cloninger's type I and type II; Babor et al.'s type A and type B), validation research has produced mixed results in terms of the construct, concurrent and predictive validity of these classifications. CONCLUSIONS: The adoption of a subtyping scheme in the major psychiatric classification systems is not recommended until further international research is conducted.

Alcoholism↗
PubMed1986

Zygomatic fractures: classification and complications.

A retrospective study of zygomatic fractures is presented in order to analyse late complications and to evaluate the different radiographic classifications. The study comprises 109 patients with 111 zygomatic fractures. The aetiology was violence in 39% and traffic accidents in 28%. Associated fractures of the craniofacial skeleton occurred in 42% of the patients. Seventy-two patients were available for the follow-up study. Malar flattening was found in 16% of the patients operated on. Thirty-four per cent of the patients had sensory disturbances, 6% had enophthalmos, and 1% had diplopia. Classifications of zygomatic fractures are reviewed. The fractures in the current study were grouped in accordance with the classifications of Knight & North and Larsen & Thomsen. Neither of these classifications was found to be useful in the preoperative evaluation of the postreductive fracture stability. The most reliable method of evaluating this stability is the preoperative evaluation, but CT classification systems may in the future demonstrate their value.

Adolescent↗
PubMed1995

Reproducibility of a histogenetic classification of thymic epithelial tumours.

A histogenetic classification of thymic epithelial neoplasms proposed by Müller-Hermelink and co-workers has been shown by a number of recent studies to be of clinical and prognostic value. Reproducibility is an important criterion for the acceptance of any new classification for general diagnostic use. The reproducibility of this classification was tested on 51 cases of thymic epithelial neoplasia, by comparing results obtained by pathologists working from published criteria only with those results obtained by the pathologists who developed the classification. In 78% of cases there was complete concordance of results. Analysis of the 22% discordant cases showed that this discordance was due to a degree of subjectivity in determining cut-off points between categories adjacent to each other in the morphological spectrum of thymic epithelial neoplasia (medullary v. mixed, cortical v. well-differentiated thymic carcinoma). In terms of the important clinical distinction between benign (medullary and mixed) thymomas and those with more aggressive biological behaviour (cortical types and well-differentiated thymic carcinoma), the degree of reproducibility was 96%. The high degree of reproducibility of this histogenetic classification of thymic epithelial neoplasms should facilitate its acceptance and use in routine diagnostic pathology.

Adolescent↗
PubMedDate not supplied

Dysontogenetic brain tumours--proposal for an improved classification.

The International World Health Organisation (WHO) classification of central nervous system tumours does not give an extensive classification of germ cell tumours and other malformative tumours and tumour-like lesions. In the same way, no consistent classification of dysontogenetic brain tumours can be found in the classical handbooks. For an eventual new edition of the WHO classification, it is proposed to reconsider and improve the classification of these tumours, based on their ontogenetic relations.

Brain↗
PubMed2006

Classifying dengue: a review of the difficulties in using the WHO case classification for dengue haemorrhagic fever.

BACKGROUND: The current World Health Organisation (WHO) classification of dengue includes two distinct entities: dengue fever (DF) and dengue haemorrhagic fever (DHF)/dengue shock syndrome; it is largely based on pediatric cases in Southeast Asia. Dengue has extended to different tropical areas and older age groups. Variations from the original description of dengue manifestations are being reported. OBJECTIVES: To analyse the experience of clinicians in using the dengue case classification and identify challenges in applying the criteria in routine clinical practice. METHOD: Systematic literature review of post-1975 English-language publications on dengue classification. RESULTS: Thirty-seven papers were reviewed. Several studies had strictly applied all four WHO criteria in DHF cases; however, most clinicians reported difficulties in meeting all four criteria and used a modified classification. The positive tourniquet test representing the minimum requirement of a haemorrhagic manifestation did not distinguish between DHF and DF. In cases of DHF thrombocytopenia was observed in 8.6-96%, plasma leakage in 6-95% and haemorrhagic manifestations in 22-93%. The low sensitivity of classifying DHF could be due to failure to repeat the tests or physical examinations at the appropriate time, early intravenous fluid therapy, and lack of adequate resources in an epidemic situation and perhaps a considerable overlap of clinical manifestations in the different dengue entities. CONCLUSION: A prospective multi-centre study across dengue endemic regions, age groups and the health care system is required which describes the clinical presentation of dengue including simple laboratory parameters in order to review and if necessary modify the current dengue classification.

Capillary Permeability↗
PubMed1996

Proposal for a pathogenesis-based classification of tumoral calcinosis.

BACKGROUND: Deposition of calcium in skin is currently categorized into a group of disorders referred to as calcinosis cutis. Divisions between types and subtypes within this confusing classification are predominantly based on morphologic differences in the calcification and serve to obscure pathogenesis. This is especially evident in a subtype of calcinosis cutis, known as tumoral calcinosis. Calcifications in cases of tumoral calcinosis share the following characteristics, but without evidence of a common pathogenesis: large size, juxtaarticular location, progressive enlargement over time, a tendency to recur after surgical removal, and an ability to encase adjacent normal structures. The goal of this study was to formulate a pathogenesis-based classification for cases of tumoral calcinosis. METHODS: In a literature review 121 cases of tumoral calcinosis were identified. These cases, along with a case evaluated in our clinic, were reviewed retrospectively, and their features compared. RESULTS: Analysis suggests three pathogenetically distinct subtypes of tumoral calcinosis: (1) Primary normophosphatemic tumoral calcinosis: patients have normal serum phosphate, normal serum calcium, and no evidence of disorders previously associated with soft tissue calcification; (2) primary hyperphosphatemic tumoral calcinosis: patents have elevated serum phosphate, normal serum calcium, and no evidence of disorders previously associated with soft tissue calcification; and (3) secondary tumoral calcinosis: patients have a concurrent disease capable of causing soft tissue calcification. Justification for this classification is based on the presence or absence of disorders known to promote soft tissue calcification and statistically significant differences in family history, mean calcification number, mean serum phosphate level, and calcification recurrence after excision. CONCLUSIONS: A classification for tumoral calcinosis is devised that outlines potential pathogenetic mechanisms and predicts response to therapy and prognosis. Analysis of other forms of calcinosis cutis may reveal definable pathogenetic differences that suggest a coherent classification for all cutaneous calcinoses.

Adolescent↗
PubMed1998

Treatment of metastatic nonseminomatous germ cell tumors of the testis: significance of the international consensus prognostic classification as a prognostic factor-based staging system.

BACKGROUND: We reviewed treatment results in patients with metastatic nonseminomatous germ cell tumors of the testis and examined the significance of the International Consensus Prognostic Classification to make appropriate risk-based decisions concerning induction chemotherapy. METHODS: We divided 37 patients treated with platinum-based combination chemotherapy into good, intermediate, and poor prognostic groups utilizing the International Consensus Prognostic Classification. The data was analyzed for both overall survival and progression-free survival among the 3 prognostic groups. RESULTS: Among the 37 patients, 10 died (8 of progressive disease, 1 of pneumonia during induction chemotherapy and 1 of cyclophosphamide-induced hemorrhagic cardiomyolitis during salvage chemotherapy). The survivors were followed for 6 to 1 84 months from the beginning of induction chemotherapy (median, 80 months). Five of the 37 patients (14%) were classified as having a good prognosis, 1 8 (48%) as intermediate, and 14 (38%) as having a poor prognosis. The patients in the poor prognostic group had a 5-year overall survival of only 40%, while those in the good and intermediate groups had 5-year overall survivals of 100% and 94%, respectively. When we applied the International Consensus Prognostic Classification to patients with advanced disease classified by the Indiana University Staging System, these patients could be clearly divided into good-risk and poor-risk groups. CONCLUSIONS: The International Consensus Prognostic Classification is easily applicable and accurate for risk assessment in patients with metastatic nonseminomatous germ cell tumors of the testis. This classification will now be widely used in general oncology practices and for clinical trials in these patients.

Adolescent↗