Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “mutual information”

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 91 records · Page 5Linked to original sources
PubMed2003

Scoring and identifying organism-specific functional patterns and putative phosphorylation sites in protein sequences using mutual information.

The co-variance of amino acid positions within a multiple alignment of 294 protein kinases from mammals, plants, and bacteria was studied. Applying mutual information (MI), characteristic amino acid sites have been identified markedly discriminating the different organisms. The relation of surface accessibility of these sites in the 3D structure of a kinase and their MI content is studied. We extended the method to score a predicted phosphorylation site of this highly conserved catalytic protein kinase region. Based on this score mammalian and plant protein kinases were grouped together apart from the bacterial kinases. Thus, the presented method allows us to analyse putative phosphorylation sites in the context of their organism-specific origin.

Amino Acid Sequence↗
PubMed2001

Application of the mutual information criterion for feature selection in computer-aided diagnosis.

The purpose of this study was to investigate an information theoretic approach to feature selection for computer-aided diagnosis (CAD). The approach is based on the mutual information (MI) concept. MI measures the general dependence of random variables without making any assumptions about the nature of their underlying relationships. Consequently, MI can potentially offer some advantages over feature selection techniques that focus only on the linear relationships of variables. This study was based on a database of statistical texture features extracted from perfusion lung scans. The ultimate goal was to select the optimal subset of features for the computer-aided diagnosis of acute pulmonary embolism (PE). Initially, the study addressed issues regarding the approximation of MI in a limited dataset as it is often the case in CAD applications. The MI selected features were compared to those features selected using stepwise linear discriminant analysis and genetic algorithms for the same PE database. Linear and nonlinear decision models were implemented to merge the selected features into a final diagnosis. Results showed that the MI is an effective feature selection criterion for nonlinear CAD models overcoming some of the well-known limitations and computational complexities of other popular feature selection techniques in the field.

Diagnosis, Computer-Assisted↗
PubMed1997

Demonstration of accuracy and clinical versatility of mutual information for automatic multimodality image fusion using affine and thin-plate spline warped geometric deformations.

This paper applies and evaluates an automatic mutual information-based registration algorithm across a broad spectrum of multimodal volume data sets. The algorithm requires little or no pre-processing, minimal user input and easily implements either affine, i.e. linear or thin-plate spline (TPS) warped registrations. We have evaluated the algorithm in phantom studies as well as in selected cases where few other algorithms could perform as well, if at all, to demonstrate the value of this new method. Pairs of multimodal gray-scale volume data sets were registered by iteratively changing registration parameters to maximize mutual information. Quantitative registration errors were assessed in registrations of a thorax phantom using PET/CT and in the National Library of Medicine's Visible Male using MRI T2-/T1-weighted acquisitions. Registrations of diverse clinical data sets were demonstrated including rotate-translate mapping of PET/MRI brain scans with significant missing data, full affine mapping of thoracic PET/CT and rotate-translate mapping of abdominal SPECT/CT. A five-point thin-plate spline (TPS) warped registration of thoracic PET/CT is also demonstrated. The registration algorithm converged in times ranging between 3.5 and 31 min for affine clinical registrations and 57 min for TPS warping. Mean error vector lengths for rotate-translate registrations were measured to be subvoxel in phantoms. More importantly the rotate-translate algorithm performs well even with missing data. The demonstrated clinical fusions are qualitatively excellent at all levels. We conclude that such automatic, rapid, robust algorithms significantly increase the likelihood that multimodality registrations will be routinely used to aid clinical diagnoses and post-therapeutic assessment in the near future.

Abdomen↗
PubMedDate not supplied

Gene mapping and marker clustering using Shannon's mutual information.

Finding the causal genetic regions underlying complex traits is one of the main aims in human genetics. In the context of complex diseases, which are believed to be controlled by multiple contributing loci of largely unknown effect and position, it is especially important to develop general yet sensitive methods for gene mapping. We discuss the use of Shannon's information theory for population-based gene mapping of discrete and quantitative traits and for marker clustering. Various measures of mutual information were employed in order to develop a comprehensive framework for gene mapping analyses. An algorithm aimed at finding so-called relevance chains of causal markers is proposed. Moreover, entropy measures are used in conjunction with multidimensional scaling to visualize clusters of genetic markers. The relevance chain algorithm successfully detected the two causal regions in a simulated scenario. The approach has also been applied to a published clinical study on autoimmune (Graves') disease. Results were consistent with those of standard statistical methods, but identified an additional locus of interest in the promotor region of the associated gene CTLA4. The developed software is freely available at http://www.Int.ei.tum.de/download/InfoGeneMap/.

Algorithms↗
PubMed1994

Sequence comparisons via algorithmic mutual information.

One of the main problems in DNA and protein sequence comparisons is to decide whether observed similarity of two sequences should be explained by their relatedness or by mere presence of some shared internal structure, e.g., shared internal tandem repeats. The standard methods that are based on statistics or classical information theory can be used to discover either internal structure or mutual sequence similarity, but cannot take into account both. Consequently, currently used methods for sequence comparison employ "masking" techniques that simply eliminate sequences that exhibit internal repetitive structure prior to sequence comparisons. The "masking" approach precludes discovery of homologous sequences of moderate or low complexity, which abound at both DNA and protein levels. As a solution to this problem, we propose a general method that is based on algorithmic information theory and minimal length encoding. We show that algorithmic mutual information factors out the sequence similarity that is due to shared internal structure and thus enables discovery of truly related sequences. We extend that recently developed algorithmic significance method (Milosavljević & Jurka 1993) to show that significance depends exponentially on algorithmic mutual information.

Algorithms↗
PubMedDate not supplied

[Study of phylogenetic relations of hantaviruses by using the mutual information method. Tula genotype viruses].

Phylogenetic relations were studied in the group of Tula viruses (Hantavirus genus, Bunyaviridae family) of Eurasia. The similarity in the nucleotide sequences of segments was estimated by the value of mutual information. The application of this method confirmed that recombinant events might occur in some Tula-like viruses of Eurasia, as previously presumed by the results of bootscanning and analysis of amino acid sequences. It was found that might be recombination between distinct phylogenetic Tula sublineages; concepts of the microevolution of the group as a whole are specified.

Databases, Factual↗
PubMed2006

Retrospective distortion correction for 3D MR diffusion tensor microscopy using mutual information and Fourier deformations.

Magnetic resonance diffusion tensor imaging (DTI) can be complicated by distortions that contribute to errors in tissue characterization and loss of fine structures. This work presents a correction scheme based on retrospective registration via mutual information (MI), using Fourier transform (FT)-based deformations to enhance the reliability of the entropy-based image registration. The registration methodology is applied to correct distortions in 3D high-resolution DTI datasets, incorporating a complete set of affine deformations. The results demonstrate that the proposed methodology can consistently and significantly reduce the number of misregistered pixels, leading to marked improvement in the visualization of internal brain white matter (WM) structure via DTI. Post-registration analysis revealed that eddy-current effects cannot fully account for the observed image distortions. Combined, these findings support the non-model-based, postprocessing approach for correcting distortions, and demonstrate the advantages of combining FT-based deformations and MI registration to enhance the practical utility of DTI.

Animals↗
PubMed2005

Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy.

Feature selection is an important problem for pattern classification systems. We study how to select good features according to the maximal statistical dependency criterion based on mutual information. Because of the difficulty in directly implementing the maximal dependency condition, we first derive an equivalent form, called minimal-redundancy-maximal-relevance criterion (mRMR), for first-order incremental feature selection. Then, we present a two-stage feature selection algorithm by combining mRMR and other more sophisticated feature selectors (e.g., wrappers). This allows us to select a compact set of superior features at very low cost. We perform extensive experimental comparison of our algorithm and other methods using three different classifiers (naive Bayes, support vector machine, and linear discriminate analysis) and four different data sets (handwritten digits, arrhythmia, NCI cancer cell lines, and lymphoma tissues). The results confirm that mRMR leads to promising improvement on feature selection and classification accuracy.

Algorithms↗
PubMed2005

Recognizing names in biomedical texts using mutual information independence model and SVM plus sigmoid.

In this paper, we present a biomedical name recognition system, called PowerBioNE. In order to deal with the special phenomena in the biomedical domain, various evidential features are proposed and integrated through a mutual information independence model (MIIM). In addition, a support vector machine (SVM) plus sigmoid is proposed to resolve the data sparseness problem in the MIIM. In this way, the data sparseness problem in MIIM-based biomedical name recognition can be resolved effectively and a biomedical name recognition system with better performance and better portability can be achieved. Finally, we present two post-processing modules to deal with the nested entity name and abbreviation phenomena in the biomedical domain to further improve the performance. Evaluation shows that our system achieves F-measures of 69.1 and 71.2 on the 23 classes of GENIA V1.1 and V3.0, respectively. In particular, our system achieves an F-measure of 77.8 on the "protein" class of GENIA V3.0. It also shows that our system outperforms the best-reported system on GENIA V1.1 and V3.0.

Abstracting and Indexing↗
PubMed2000

Comparison of rigid and elastic matching of dynamic magnetic resonance mammographic images by mutual information.

The present study aims at (i) the evaluation of the performance of a rigid and of an elastic matching algorithm for the coregistration of dynamic magnetic resonance (MR) images visualizing the female breast, and (ii) the evaluation of the mutual information (MI) as a matching criterion. To this end, ten patient data sets were analyzed. The comparison was performed with respect to the achieved increase in the MI and by visual inspection of the dynamic image series in a continuous film sequence ((cine mode). In most cases, the achieved increase in MI by elastic image registration is much higher than that achieved by rigid registration. Only for three of the ten data sets could the MI be increased by rigid image registration to a similar or even larger degree than by elastic image registration. Taking into account the results of the visual inspection of the rigid and elastic matched data sets, however, the elastic match leads to equal or better results for all data sets. Therefore, elastic matching is the gold standard for the registration of dynamic MR mammographic images of the female breast. The comparison of the increase in MI and the visual inspection further shows that the visual impression agrees in most cases with the result of the calculation of the MI. Therefore, the MI proves to be a suitable matching criterion for the type of data sets studied.

Algorithms↗
PubMed1996

Multi-modal volume registration by maximization of mutual information.

A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position and orientation until the mutual information between the images is maximized. In our derivation of the registration procedure, few assumptions are made about the nature of the imaging process. As a result the algorithms are quite general and can foreseeably be used with a wide variety of imaging devices. This approach works directly with image data; no pre-processing or segmentation is required. This technique is, however, more flexible and robust than other intensity-based techniques like correlation. Additionally, it has an efficient implementation that is based on stochastic approximation. Experiments are presented that demonstrate the approach registering magnetic resonance (MR) images with computed tomography (CT) images, and with positron-emission tomography (PET) images. Surgical applications of the registration method are described.

Brain↗
PubMed2006

Maximization of mutual information for offline Thai handwriting recognition.

This paper aims to improve the performance of an HMM-based offline Thai handwriting recognition system through discriminative training and the use of fine-tuned feature extraction methods. The discriminative training is implemented by maximizing the mutual information between the data and their classes. The feature extraction is based on our proposed block-based PCA and composite images, shown to be better at discriminating Thai confusable characters. We demonstrate significant improvements in recognition accuracies compared to the classifiers that are not discriminatively optimized.

Algorithms↗
PubMed2001

Quantitative analysis of termination of vagally induced canine atrial fibrillation by mutual information.

Atrial fibrillation (AF) is often described as a disorganized phenomenon, but many features that qualitatively suggest an underlying order have recently been reported. The present study aimed to disclose this underlying order of AF in a quantitative manner, using a new method of mutual information (MI), which is a measure for gauging the general correlation between 2 time series. Frequency analysis and the MI method were used to analyze 5 epicardial potentials on both atria during AF induced by vagal stimulation (Vs) in 15 dogs. Unipolar electrodes were placed on the right atrial appendage (Rap), the high right atrium (HRA), and the left atrial appendage (Lap). The other 2 electrodes were placed equidistantly between HRA and Rap (RA1-RA2). The power spectrum of AF had a discrete peak around 17Hz during Vs. After Vs was stopped, the discrete peak shifted from 17Hz to 7 Hz on all epicardial leads. Taking RA2 as a reference, MI was calculated between RA2 and each of the other electrodes. The MI values (0.066+/-0.005) were greater than 0.047 (the critical value for correlated data) even during Vs. The MI values increased significantly from the highly active process of AF during Vs to the less active one (0.126+/-0.006) before termination of AF. In addition, the MI values increased more at the electrodes close to RA2 (RA1 and Rap) than at those far from it (HRA and Lap). These findings suggest that multiple wavelets, which are not random, progressively organize into a few major waves toward the termination of AF; therefore, AF is not a random phenomenon in this model.

Animals↗
PubMed2006

Fingerprint registration by maximization of mutual information.

Fingerprint registration is a critical step in fingerprint matching. Although a variety of registration alignment algorithms have been proposed, accurate fingerprint registration remains an unresolved problem. We propose a new algorithm for fingerprint registration using orientation field. This algorithm finds the correct alignment by maximization of mutual information between features extracted from orientation fields of template and input fingerprint images. Orientation field, representing the flow of ridges, is a relatively stable global feature of fingerprint images. This method uses the statistics and distribution of global feature of fingerprint images so that it is robust to image quality and local changes in images. The primary characteristic of this method is that it uses this stable global feature to align fingerprints, and that its behavior may resemble the way humans compare fingerprints. Experimental results show that the occurrence of misalignment is dramatically reduced and that registration accuracy is greatly improved at the same time, leading to enhanced matching performance.

Algorithms↗
PubMed2001

A feasibility study of mutual information based setup error estimation for radiotherapy.

We have investigated a fully automatic setup error estimation method that aligns DRRs (digitally reconstructed radiographs) from a three-dimensional planning computed tomography image onto two-dimensional radiographs that are acquired in a treatment room. We have chosen a MI (mutual information)-based image registration method, hoping for robustness to intensity differences between the DRRs and the radiographs. The MI-based estimator is fully automatic since it is based on the image intensity values without segmentation. Using 10 repeated scans of an anthropomorphic chest phantom in one position and two single scans in two different positions, we evaluated the performance of the proposed method and a correlation-based method against the setup error determined by fiducial marker-based method. The mean differences between the proposed method and the fiducial marker-based method were smaller than 1 mm for translational parameters and 0.8 degree for rotational parameters. The standard deviations of estimates from the proposed method due to detector noise were smaller than 0.3 mm and 0.07 degree for the translational parameters and rotational parameters, respectively.

Algorithms↗
PubMed2006

Neighborhood detection using mutual information for the identification of cellular automata.

Extracting the rules from spatio-temporal patterns generated by the evolution of cellular automata (CA) usually requires a priori information about the observed system, but in many applications little information will be known about the pattern. This paper introduces a new neighborhood detection algorithm which can determine the range of the neighborhood without any knowledge of the system by introducing a criterion based on mutual information (and an indication of over-estimation). A coarse-to-fine identification routine is then proposed to determine the CA rule from the observed pattern. Examples, including data from a real experiment, are employed to evaluate the new algorithm.

Algorithms↗
PubMed2003

Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information.

The purpose of this study was to develop a knowledge-based scheme for the detection of masses on digitized screening mammograms. The computer-assisted detection (CAD) scheme utilizes a knowledge databank of mammographic regions of interest (ROIs) with known ground truth. Each ROI in the databank serves as a template. The CAD system follows a template matching approach with mutual information as the similarity metric to determine if a query mammographic ROI depicts a true mass. Based on their information content, all similar ROIs in the databank are retrieved and rank-ordered. Then, a decision index is calculated based on the query's best matches. The decision index effectively combines the similarity indices and ground truth of the best-matched templates into a prediction regarding the presence of a mass in the query mammographic ROI. The system was developed and evaluated using a database of 1465 ROIs extracted from the Digital Database for Screening Mammography. There were 809 ROIs with confirmed masses (455 malignant and 354 benign) and 656 normal ROIs. CAD performance was assessed using a leave-one-out sampling scheme and Receiver Operating Characteristics analysis. Depending on the formulation of the decision index, CAD performance as high as A(zeta) = 0.87 +/- 0.01 was achieved. The CAD detection rate was consistent for both malignant and benign masses. In addition, the impact of certain implementation parameters on the detection accuracy and speed of the proposed CAD scheme was studied in more detail.

Algorithms↗
PubMed2001

Graph matching vs mutual information maximization for object detection.

Labeled Graph Matching (LGM) has been shown successful in numerous object vision tasks. This method is the basis for arguably the best face recognition system in the world. We present an algorithm for visual pattern recognition that is an extension of LGM ('LGM+'). We compare the performance of LGM and LGM+ algorithms with a state of the art statistical method based on Mutual Information Maximization (MIM). We present an adaptation of the MIM method for multi-dimensional Gabor wavelet features. The three pattern recognition methods were evaluated on an object detection task, using a set of stimuli on which none of the methods had been tested previously. The results indicate that while the performance of the MIM method operating upon Gabor wavelets is superior to the same method operating on pixels and to LGM, it is surpassed by LGM+. LGM+ offers a significant improvement in performance over LGM without losing LGM' s virtues of simplicity, biological plausibility, and a computational cost that is 2-3 orders of magnitude lower than that of the MIM algorithm.

Algorithms↗