SEARCH · PubMed Health

Results for “Clustering Algorithms”

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 1,189 records · Page 66Linked to original sources

PubMed2003

Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography.

In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765 sections), which contained 71 confirmed nodules including 66 biopsy-confirmed primary cancers, from a lung cancer screening program. The Multi-MTANN was applied to 58 true positives (nodules from 54 patients) and 1726 false positives (non-nodules) reported by our current scheme in a validation test; these were different from the training set. The results indicated that 83% (1424/1726) of non-nodules were removed with a reduction of one true positive (nodule), i.e., a classification sensitivity of 98.3% (57 of 58 nodules). By using the Multi-MTANN, the false-positive rate of our current scheme was improved from 0.98 to 0.18 false positives per section (from 27.4 to 4.8 per patient) at an overall sensitivity of 80.3% (57/71).

Algorithms↗

PubMed2003

Detection of prostate cancer by integration of line-scan diffusion, T2-mapping and T2-weighted magnetic resonance imaging; a multichannel statistical classifier.

A multichannel statistical classifier for detecting prostate cancer was developed and validated by combining information from three different magnetic resonance (MR) methodologies: T2-weighted, T2-mapping, and line scan diffusion imaging (LSDI). From these MR sequences, four different sets of image intensities were obtained: T2-weighted (T2W) from T2-weighted imaging, Apparent Diffusion Coefficient (ADC) from LSDI, and proton density (PD) and T2 (T2 Map) from T2-mapping imaging. Manually segmented tumor labels from a radiologist, which were validated by biopsy results, served as tumor "ground truth." Textural features were extracted from the images using co-occurrence matrix (CM) and discrete cosine transform (DCT). Anatomical location of voxels was described by a cylindrical coordinate system. A statistical jack-knife approach was used to evaluate our classifiers. Single-channel maximum likelihood (ML) classifiers were based on 1 of the 4 basic image intensities. Our multichannel classifiers: support vector machine (SVM) and Fisher linear discriminant (FLD), utilized five different sets of derived features. Each classifier generated a summary statistical map that indicated tumor likelihood in the peripheral zone (PZ) of the prostate gland. To assess classifier accuracy, the average areas under the receiver operator characteristic (ROC) curves over all subjects were compared. Our best FLD classifier achieved an average ROC area of 0.839(+/-0.064), and our best SVM classifier achieved an average ROC area of 0.761(+/-0.043). The T2W ML classifier, our best single-channel classifier, only achieved an average ROC area of 0.599(+/-0.146). Compared to the best single-channel ML classifier, our best multichannel FLD and SVM classifiers have statistically superior ROC performance (P=0.0003 and 0.0017, respectively) from pairwise two-sided t-test. By integrating the information from multiple images and capturing the textural and anatomical features in tumor areas, summary statistical maps can potentially aid in image-guided prostate biopsy and assist in guiding and controlling delivery of localized therapy under image guidance.

Algorithms↗

PubMed2004

Influence of x-ray pulse parameters on the image quality for moving objects in digital cardiac imaging.

The image quality of a single frame in a modern cardiac imaging x-ray facility can be improved by adjusting the automatic pulse exposure parameters. The effects of acquisition rate on patient dose and the detectability of moving objects have been fully described in scientific literature. However, the influence of automatic pulse exposure parameters is still to be determined. Images of a moving wheel (with lead wires) were acquired using an H5000 Philips Integris cardiac x-ray system. Poly(methylmethacrylate) plastic samples 20 and 30 cm thick were employed as the build-up phantom to simulate a patient. The images were obtained using preset clinical parameters for cardiac imaging procedures. The signal detectability and motion blur of a contrast bar at a transversal speed in the range of 100-150 mm/s were evaluated with a cine pulse width of 3, 5, 7, and 10 ms under automatic mA kV regulation. Two levels of exposure at the image intensifier entrance were included in this study. Signal detectability was analyzed in terms of the signal-to-noise ratio (SNR) and the value of SNR2/entrance surface dose. The blurring was modeled as a Gaussian-shaped blurring function, and the motion blur was expressed in terms of the peak full width at half maximum and amplitude (apparent contrast) of the resolution functions. A contrast bar simulating a vessel in motion at the maximum velocities of typical cardiac structures was exposed. Severe loss of image quality occurred at pulse widths > or =7 ms. It is also shown that below 5 ms static nonlinearities, likely caused by the need to use a large focus for cine acquisition, dominate the blurring process.

Algorithms↗

PubMed2006

Classification of vocalizations of killer whales using dynamic time warping.

A large number of killer whale sounds have recently been classified perceptually into Call Types. [A. Hodgins-Davis, thesis, Wellesley College (2004)]. The repetition rate of the pulsed component of five or more examples of each call type has been calculated using a modified form of the FFT based comb-filter method. A dissimilarity or distance matrix for these sounds was calculated using dynamic time warping to compare their melodic contours. These distances were transformed into a component space using multidimensional scaling and the resulting points were clustered with a kmeans algorithm. In grouping 57 sounds into 9 call types, a single discrepancy between the perceptual and the automated methods occurred.

Algorithms↗

PubMed2003

Use of genetic profiling in leprosy to discriminate clinical forms of the disease.

Leprosy presents as a clinical and immunological spectrum of disease. With the use of gene expression profiling, we observed that a distinction in gene expression correlates with and accurately classifies the clinical form of the disease. Genes belonging to the leukocyte immunoglobulin-like receptor (LIR) family were significantly up-regulated in lesions of lepromatous patients suffering from the disseminated form of the infection. In functional studies, LIR-7 suppressed innate host defense mechanisms by shifting monocyte production from interleukin-12 toward interleukin-10 and by blocking antimicrobial activity triggered by Toll-like receptors. Gene expression profiles may be useful in defining clinical forms of disease and providing insights into the regulation of immune responses to pathogens.

Algorithms↗

PubMed2000

Regulatory networks revealed by transcriptional profiling of damaged Saccharomyces cerevisiae cells: Rpn4 links base excision repair with proteasomes.

Exposure to carcinogenic alkylating agents, oxidizing agents, and ionizing radiation modulates transcript levels for over one third of Saccharomyces cerevisiae's 6,200 genes. Computational analysis delineates groups of coregulated genes whose upstream regions bear known and novel regulatory sequence motifs. One group of coregulated genes contain a number of DNA excision repair genes (including the MAG1 3-methyladenine DNA glycosylase gene) and a large selection of protein degradation genes. Moreover, transcription of these genes is modulated by the proteasome-associated protein Rpn4, most likely via its binding to MAG1 upstream repressor sequence 2-like elements, that turn out to be almost identical to the recently identified proteasome-associated control element (G. Mannhaupt, R. Schnall, V. Karpov, I. Vetter, and H. Feldmann, FEBS Lett. 450:27-34, 1999). We have identified a large number of genes whose transcription is influenced by Rpn4p.

Algorithms↗

PubMed2001

Analyzing sensory systems with the information distortion function.

The nature and information content of neural signals have been discussed extensively in the neuroscience community. They are important ingredients in many theories on neural function, yet there is still no agreement on the details of neural coding. There have been various suggestions about how information is encoded in neural spike trains: by the number of spikes, by temporal correlations, through single spikes, or by spike patterns in one, or across many neurons. The latter scheme is most general and encompasses many others. We present an algorithm which can recover a coarse representation of a pattern coding scheme, through quantization to a reproduction set of smaller size. Among many possible quantizations, we choose one which preserves as much of the informativeness of the original stimulus/response relation as possible, through the use of an information-based distortion function. This method allows us to study coarse but highly informative models of a coding scheme, and then to refine them when more data becomes available. We shall describe a model in which full recovery is possible and present example for cases with partial recovery.

Algorithms↗

PubMed2005

Differentiation of follicular thyroid adenoma from carcinoma by means of gene expression profiling with adapter-tagged competitive polymerase chain reaction.

OBJECTIVE: Since preoperative differentiation between follicular thyroid adenoma (FTA) and carcinoma (FTC) remains very difficult, the purpose of this study was to identify the genes differentially expressed in FTA and FTC in order to construct a diagnostic system based on such genes for differentiation of FTA and FTC. METHODS: Gene expression profiles of 45 FTAs and 22 FTCs were analyzed by means of adapter-tagged competitive polymerase chain reaction (ATAC-PCR) with 2,516 genes (learning set). The genes differentially expressed in FTAs and FTCs were then used to construct a diagnostic system based on the weighted-voting algorithm. In addition, a validation study of this diagnostic system was conducted using 12 FTAs and 6 FTCs (validation set). RESULTS: The diagnostic system for differentiation of FTA and FTC, constructed with the aid of the learning set samples, was based on 60 genes differentially expressed in FTA and FTC, which included several genes previously identified as overexpressed in FTC (DPP4, KRT19 and IGFBP3) or FTA (trefoil factor 3 and thyroid peroxidase). The leave-one-out cross-validation study showed that the accuracy of this diagnostic system was as high as 90% (sensitivity: 77.3% and specificity: 95.6%), and was confirmed by the validation study (diagnostic accuracy: 83.3%; 95% confidence interval: 62.8-95.4%, sensitivity: 66.7% and specificity: 91.2%). CONCLUSIONS: This diagnostic system using the ATAC-PCR assay is expected to be clinically useful for preoperative differentiation between FTA and FTC since ATAC-PCR can be used for the small amount of RNA obtained from fine needle aspiration biopsy.

Adenoma↗

PubMed1991

Gonadotropin secretion during aging in postmenopausal women.

Although chronological aging is known to result in reduced gonadotropin secretion in women, the precise mechanisms to account for this neuroendocrine manifestation are yet obscure. To evaluate the extent to which the pituitary and/or hypothalamus are involved in the process of aging, we aimed at characterizing the unstimulated and GnRH-stimulated gonadotropin secretion in postmenopausal women (PMW) of different ages. Accordingly, 9 younger PMW (mean age: 53.8 years) in their first and 9 older PMW (mean age: 80.3 years) in their 4th decade of life after natural onset of menopause were studied. In both groups, blood was collected at 10-min intervals for 10 h, while GnRH (25 micrograms i.v.) was administered 8 h after initiation of blood samplings. Compared to younger PMW, basal serum concentrations of dehydroepiandrosterone-sulfate were lower (p less than 0.05) in older PMW, while estrogen (estradiol, estrone), androgen (testosterone, androstendione) and sex hormone binding globulin levels were similar. Lower (p less than 0.01) mean LH levels composed of attenuated (p less than 0.05) LH pulse amplitudes and pulse frequencies (as determined by the cluster pulse algorithm) were found in the 8-hour LH secretory profiles of older PMW. Furthermore, the FSH secretion of older PMW was characterized by lower (p less than 0.01) mean FSH levels with lower (p less than 0.05) FSH pulse amplitudes, but not pulse frequencies. The absolute peak concentrations attained and the total amount of LH and FSH released in response to GnRH stimulations were blunted (p less than 0.001) in older PMW.(ABSTRACT TRUNCATED AT 250 WORDS)

Aging↗

PubMed1997

A penalty-function approach for pruning feedforward neural networks.

This article proposes the use of a penalty function for pruning feedforward neural network by weight elimination. The penalty function proposed consists of two terms. The first term is to discourage the use of unnecessary connections, and the second term is to prevent the weights of the connections from taking excessively large values. Simple criteria for eliminating weights from the network are also given. The effectiveness of this penalty function is tested on three well-known problems: the contiguity problem, the parity problems, and the monks problems. The resulting pruned networks obtained for many of these problems have fewer connections than previously reported in the literature.

Algorithms↗

PubMed1997

Medical image analysis with fuzzy models.

This paper updates several recent surveys on the use of fuzzy models for segmentation and edge detection in medical image data. Our survey is divided into methods based on supervised and unsupervised learning (that is, on whether there are or are not labelled data available for supervising the computations), and is organized first and foremost by groups (that we know of!) that are active in this area. Our review is aimed more towards 'who is doing it' rather than 'how good it is'. This is partially dictated by the fact that direct comparisons of supervised and unsupervised methods is somewhat akin to comparing apples and oranges. There is a further subdivision into methods for two- and three-dimensional data and/or problems. We do not cover methods based on neural-like networks or fuzzy reasoning systems. These topics are covered in a recently published companion survey by keller et al.

Algorithms↗

PubMed2001

FastGroup: a program to dereplicate libraries of 16S rDNA sequences.

BACKGROUND: Ribosomal 16S DNA sequences are an essential tool for identifying and classifying microbes. High-throughput DNA sequencing now makes it economically possible to produce very large datasets of 16S rDNA sequences in short time periods, necessitating new computer tools for analyses. Here we describe FastGroup, a Java program designed to dereplicate libraries of 16S rDNA sequences. By dereplication we mean to: 1) compare all the sequences in a data set to each other, 2) group similar sequences together, and 3) output a representative sequence from each group. In this way, duplicate sequences are removed from a library. RESULTS: FastGroup was tested using a library of single-pass, bacterial 16S rDNA sequences cloned from coral-associated bacteria. We found that the optimal strategy for dereplicating these sequences was to: 1) trim ambiguous bases from the 5' end of the sequences and all sequence 3' of the conserved Bact517 site, 2) match the sequences from the 3' end, and 3) group sequences > or =97% identical to each other. CONCLUSIONS: The FastGroup program simplifies the dereplication of 16S rDNA sequence libraries and prepares the raw sequences for subsequent analyses.

Algorithms↗

PubMed2005

FACT--a framework for the functional interpretation of high-throughput experiments.

BACKGROUND: Interpreting the results of high-throughput experiments, such as those obtained from DNA-microarrays, is an often time-consuming task due to the high number of data-points that need to be analyzed in parallel. It is usually a matter of extensive testing and unknown beforehand, which of the possible approaches for the functional analysis will be the most informative. RESULTS: To address this problem, we have developed the Flexible Annotation and Correlation Tool (FACT). FACT allows for detection of important patterns in large data sets by simplifying the integration of heterogeneous data sources and the subsequent application of different algorithms for statistical evaluation or visualization of the annotated data. The system is constantly extended to include additional annotation data and comparison methods. CONCLUSION: FACT serves as a highly flexible framework for the explorative analysis of large genomic and proteomic result sets. The program can be used online; open source code and supplementary information are available at http://www.factweb.de.

Algorithms↗

PubMed2005

JACOP: a simple and robust method for the automated classification of protein sequences with modular architecture.

BACKGROUND: Whole-genome sequencing projects are rapidly producing an enormous number of new sequences. Consequently almost every family of proteins now contains hundreds of members. It has thus become necessary to develop tools, which classify protein sequences automatically and also quickly and reliably. The difficulty of this task is intimately linked to the mechanism by which protein sequences diverge, i.e. by simultaneous residue substitutions, insertions and/or deletions and whole domain reorganisations (duplications/swapping/fusion). RESULTS: Here we present a novel approach, which is based on random sampling of sub-sequences (probes) out of a set of input sequences. The probes are compared to the input sequences, after a normalisation step; the results are used to partition the input sequences into homogeneous groups of proteins. In addition, this method provides information on diagnostic parts of the proteins. The performance of this method is challenged by two data sets. The first one contains the sequences of prokaryotic lyases that could be arranged as a multiple sequence alignment. The second one contains all proteins from Swiss-Prot Release 36 with at least one Src homology 2 (SH2) domain--a classical example for proteins with modular architecture. CONCLUSION: The outcome of our method is robust, highly reproducible as shown using bootstrap and resampling validation procedures. The results are essentially coherent with the biology. This method depends solely on well-established publicly available software and algorithms.

Algorithms↗

PubMed2005

Two-part permutation tests for DNA methylation and microarray data.

BACKGROUND: One important application of microarray experiments is to identify differentially expressed genes. Often, small and negative expression levels were clipped-off to be equal to an arbitrarily chosen cutoff value before a statistical test is carried out. Then, there are two types of data: truncated values and original observations. The truncated values are not just another point on the continuum of possible values and, therefore, it is appropriate to combine two statistical tests in a two-part model rather than using standard statistical methods. A similar situation occurs when DNA methylation data are investigated. In that case, there are null values (undetectable methylation) and observed positive values. For these data, we propose a two-part permutation test. RESULTS: The proposed permutation test leads to smaller p-values in comparison to the original two-part test. We found this for both DNA methylation data and microarray data. With a simulation study we confirmed this result and could show that the two-part permutation test is, on average, more powerful. The new test also reduces, without any loss of power, to a standard test when there are no null or truncated values. CONCLUSION: The two-part permutation test can be used in routine analyses since it reduces to a standard test when there are positive values only. Further advantages of the new test are that it opens the possibility to use other test statistics to construct the two-part test and that it avoids the use of any asymptotic distribution. The latter advantage is particularly important for the analysis of microarrays since sample sizes are usually small.

Algorithms↗

PubMed2005

Towards precise classification of cancers based on robust gene functional expression profiles.

BACKGROUND: Development of robust and efficient methods for analyzing and interpreting high dimension gene expression profiles continues to be a focus in computational biology. The accumulated experiment evidence supports the assumption that genes express and perform their functions in modular fashions in cells. Therefore, there is an open space for development of the timely and relevant computational algorithms that use robust functional expression profiles towards precise classification of complex human diseases at the modular level. RESULTS: Inspired by the insight that genes act as a module to carry out a highly integrated cellular function, we thus define a low dimension functional expression profile for data reduction. After annotating each individual gene to functional categories defined in a proper gene function classification system such as Gene Ontology applied in this study, we identify those functional categories enriched with differentially expressed genes. For each functional category or functional module, we compute a summary measure (s) for the raw expression values of the annotated genes to capture the overall activity level of the module. In this way, we can treat the gene expressions within a functional module as an integrative data point to replace the multiple values of individual genes. We compare the classification performance of decision trees based on functional expression profiles with the conventional gene expression profiles using four publicly available datasets, which indicates that precise classification of tumour types and improved interpretation can be achieved with the reduced functional expression profiles. CONCLUSION: This modular approach is demonstrated to be a powerful alternative approach to analyzing high dimension microarray data and is robust to high measurement noise and intrinsic biological variance inherent in microarray data. Furthermore, efficient integration with current biological knowledge has facilitated the interpretation of the underlying molecular mechanisms for complex human diseases at the modular level.

Algorithms↗

PubMed2005

Correlation test to assess low-level processing of high-density oligonucleotide microarray data.

BACKGROUND: There are currently a number of competing techniques for low-level processing of oligonucleotide array data. The choice of technique has a profound effect on subsequent statistical analyses, but there is no method to assess whether a particular technique is appropriate for a specific data set, without reference to external data. RESULTS: We analyzed coregulation between genes in order to detect insufficient normalization between arrays, where coregulation is measured in terms of statistical correlation. In a large collection of genes, a random pair of genes should have on average zero correlation, hence allowing a correlation test. For all data sets that we evaluated, and the three most commonly used low-level processing procedures including MAS5, RMA and MBEI, the housekeeping-gene normalization failed the test. For a real clinical data set, RMA and MBEI showed significant correlation for absent genes. We also found that a second round of normalization on the probe set level improved normalization significantly throughout. CONCLUSION: Previous evaluation of low-level processing in the literature has been limited to artificial spike-in and mixture data sets. In the absence of a known gold-standard, the correlation criterion allows us to assess the appropriateness of low-level processing of a specific data set and the success of normalization for subsets of genes.

Algorithms↗

PubMed2005

Regularized Least Squares Cancer classifiers from DNA microarray data.

BACKGROUND: The advent of the technology of DNA microarrays constitutes an epochal change in the classification and discovery of different types of cancer because the information provided by DNA microarrays allows an approach to the problem of cancer analysis from a quantitative rather than qualitative point of view. Cancer classification requires well founded mathematical methods which are able to predict the status of new specimens with high significance levels starting from a limited number of data. In this paper we assess the performances of Regularized Least Squares (RLS) classifiers, originally proposed in regularization theory, by comparing them with Support Vector Machines (SVM), the state-of-the-art supervised learning technique for cancer classification by DNA microarray data. The performances of both approaches have been also investigated with respect to the number of selected genes and different gene selection strategies. RESULTS: We show that RLS classifiers have performances comparable to those of SVM classifiers as the Leave-One-Out (LOO) error evaluated on three different data sets shows. The main advantage of RLS machines is that for solving a classification problem they use a linear system of order equal to either the number of features or the number of training examples. Moreover, RLS machines allow to get an exact measure of the LOO error with just one training. CONCLUSION: RLS classifiers are a valuable alternative to SVM classifiers for the problem of cancer classification by gene expression data, due to their simplicity and low computational complexity. Moreover, RLS classifiers show generalization ability comparable to the ones of SVM classifiers also in the case the classification of new specimens involves very few gene expression levels.

Algorithms↗