A New Family of Distance Functions for Perceptual Similarity Retrieval of Medical Images

A long-standing challenge of content-based image retrieval (CBIR) systems is the definition of a suitable distance function to measure the similarity between images in an application context which complies with the human perception of similarity. In this paper, we present a new family of distance functions, called attribute concurrence influence distances (AID), which serve to retrieve images by similarity. These distances address an important aspect of the psychophysical notion of similarity in comparisons of images: the effect of concurrent variations in the values of different image attributes. The AID functions allow for comparisons of feature vectors by choosing one of two parameterized expressions: one targeting weak attribute concurrence influence and the other for strong concurrence influence. This paper presents the mathematical definition and implementation of the AID family for a two-dimensional feature space and its extension to any dimension. The composition of the AID family with L (p) distance family is considered to propose a procedure to determine the best distance for a specific application. Experimental results involving several sets of medical images demonstrate that, taking as reference the perception of the specialist in the field (radiologist), the AID functions perform better than the general distance functions commonly used in CBIR.

Supporting content-based image retrieval and computer-aided diagnosis systems with association rule-based techniques

In this work, we take advantage of association rule mining to support two types of medical systems: the Content-based Image Retrieval (CBIR) systems and the Computer-Aided Diagnosis (CAD) systems. For content-based retrieval, association rules are employed to reduce the dimensionality of the feature vectors that represent the images and to improve the precision of the similarity queries. We refer to the association rule-based method to improve CBIR systems proposed here as Feature selection through Association Rules (FAR). To improve CAD systems, we propose the Image Diagnosis Enhancement through Association rules (IDEA) method. Association rules are employed to suggest a second opinion to the radiologist or a preliminary diagnosis of a new image. A second opinion automatically obtained can either accelerate the process of diagnosing or to strengthen a hypothesis, increasing the probability of a prescribed treatment be successful. Two new algorithms are proposed to support the IDEA method: to pre-process low-level features and to propose a preliminary diagnosis based on association rules. We performed several experiments to validate the proposed methods. The results indicate that association rules can be successfully applied to improve CBIR and CAD systems, empowering the arsenal of techniques to support medical image analysis in medical systems. (C) 2009 Elsevier B.V. All rights reserved.

Etiology of cutaneous leishmaniasis and anthropophilic vectors in Juruti, Pará State, Brazil

In a preliminary study in Juruti, a mining municipality in western Pará State, Brazil, 12 out of 21 patients suspected of presenting cutaneous leishmaniasis showed positive PCR (SSUrDNA and G6PD): Leishmania (Viannia) braziliensis (9/12; 75%) and L. (V.) sp. (3/12; 25%). Entomological studies in the same location revealed the presence of 12 different phlebotomine species (n =105). One of the most common species was Lutzomyia (Psychodopygus) complexa (17%) which is both highly anthropophilic and a known vector of L. (V.) braziliensis in other regions of Pará. These preliminary findings should serve to guide future epidemiological surveillance in Juruti.

Potential vectors and hosts of rickettsia spp: epidemiological studies in the Vale do Paraíba, state of Rio de Janeiro/Brazil

FAPESP, CNPq, CAPES

Feature selection environment for genomic applications

Background: Feature selection is a pattern recognition approach to choose important variables according to some criteria in order to distinguish or explain certain phenomena (i.e., for dimensionality reduction). There are many genomic and proteomic applications that rely on feature selection to answer questions such as selecting signature genes which are informative about some biological state, e. g., normal tissues and several types of cancer; or inferring a prediction network among elements such as genes, proteins and external stimuli. In these applications, a recurrent problem is the lack of samples to perform an adequate estimate of the joint probabilities between element states. A myriad of feature selection algorithms and criterion functions have been proposed, although it is difficult to point the best solution for each application. Results: The intent of this work is to provide an open-source multiplataform graphical environment for bioinformatics problems, which supports many feature selection algorithms, criterion functions and graphic visualization tools such as scatterplots, parallel coordinates and graphs. A feature selection approach for growing genetic networks from seed genes ( targets or predictors) is also implemented in the system. Conclusion: The proposed feature selection environment allows data analysis using several algorithms, criterion functions and graphic visualization tools. Our experiments have shown the software effectiveness in two distinct types of biological problems. Besides, the environment can be used in different pattern recognition applications, although the main concern regards bioinformatics tasks.

A FEM procedure based on positions and unconstrained vectors applied to non-linear dynamic of 3D frames

This study presents an alternative three-dimensional geometric non-linear frame formulation based on generalized unconstrained vector and positions to solve structures and mechanisms subjected to dynamic loading. The formulation is classified as total Lagrangian with exact kinematics description. The resulting element presents warping and non-constant transverse strain modes, which guarantees locking-free behavior for the adopted three-dimensional constitutive relation, Saint-Venant-Kirchhoff, for instance. The application of generalized vectors is an alternative to the use of finite rotations and rigid triad`s formulae. Spherical and revolute joints are considered and selected dynamic and static examples are presented to demonstrate the accuracy and generality of the proposed technique. (C) 2010 Elsevier B.V. All rights reserved.

Voice Feature Characteristic in Morbid Obese Population

Morbid obesity is highly prevalent in the Western World, and its consequences present a real public health challenge. Voice alterations can represent one of these consequences and represent an opportunity for interference with therapeutic methods. This particularly features of the individual`s voice was the goal of the present study. A group of 45 adult volunteers of both sexes with a BMI greater than 35 Kg/m(2) was selected among patients of the Obesity Ambulatory of the Digestive Surgery Division. The control group consisted of volunteers matched by sex, age (+/- 1 year), and smoking habits, but with a BMI bellow 30 Kg/m(2). All subjects were submitted to laryngoscopic examination, audio perceptive analysis, and voice acoustics determination. Examinations were always performed by the same doctor, and diagnoses were provided by two different physician specialists in laryngology and voice. Obese individuals exhibit the following modifications in voice feature: hoarseness, murmuring, vocal instability, altered jitter and shimmer, and reduced maximum phonation times as well the presence of voice strangulation at the end of emission. The voices of individuals with morbid obesity are different of the voice of nonobese people and demonstrate significant changes in vocal characteristics.

Claudin-7 down-regulation is an important feature in oral squamous cell carcinoma

Aims: Claudins, a large family of essential tight junction (TJ) proteins, are abnormally regulated in human carcinomas, especially claudin-7. The aim of this study was to investigate claudin-7 expression and alterations in oral squamous cell carcinoma (OSCC). Methods and results: Expression of claudin-7 was analysed in 132 cases of OSCC organized in a tissue microarray. Claudin-7 mRNA transcript was evaluated using real-time polymerase chain reaction and the methylation status of the promoter was also assessed. Claudin-7 was negative in 58.3% of the cases. Loss of claudin-7 protein expression was associated with recurrence (P = 0.019), tumour size (P = 0.014), clinical stage of OSCC (P = 0.055) and disease-free survival (P = 0.015). Down-regulation of the claudin-7 mRNA transcripts was observed in 78% of the cases, in accordance with immunoexpression. Analysis of the methylation status of the promoter region of claudin-7 revealed that treatment of O28 cells (that did not express claudin-7 mRNA transcripts) with 5-Aza-2`-Deoxycytidine (5-Aza-dC) led to the re-expression of claudin-7 mRNA transcript. Conclusion: Loss of claudin-7 expression is associated with important subcellular processes in OSCC with impact on clinical parameters.

Geographical distribution of American cutaneous leishmaniasis and its phlebotomine vectors (Diptera: Psychodidae) in the state of Sao Paulo, Brazil

Background: American cutaneous leishmaniasis (ACL) is a re-emerging disease in the state of Sao Paulo, Brazil. It is important to understand both the vector and disease distribution to help design control strategies. As an initial step in applying geographic information systems (GIS) and remote sensing (RS) tools to map disease-risk, the objectives of the present work were to: (i) produce a single database of species distributions of the sand fly vectors in the state of Sao Paulo, (ii) create combined distributional maps of both the incidence of ACL and its sand fly vectors, and (iii) thereby provide individual municipalities with a source of reference material for work carried out in their area. Results: A database containing 910 individual records of sand fly occurrence in the state of Sao Paulo, from 37 different sources, was compiled. These records date from between 1943 to 2009, and describe the presence of at least one of the six incriminated or suspected sand fly vector species in 183/645 (28.4%) municipalities. For the remaining 462 (71.6%) municipalities, we were unable to locate records of any of the six incriminated or suspected sand fly vector species (Nyssomyia intermedia, N. neivai, N. whitmani, Pintomyia fischeri, P. pessoai and Migonemyia migonei). The distribution of each of the six incriminated or suspected vector species of ACL in the state of Sao Paulo were individually mapped and overlaid on the incidence of ACL for the period 1993 to 1995 and 1998 to 2007. Overall, the maps reveal that the six sand fly vector species analyzed have unique and heterogeneous, although often overlapping, distributions. Several sand fly species - Nyssomyia intermedia and N. neivai - are highly localized, while the other sand fly species - N. whitmani, M. migonei, P. fischeri and P. pessoai - are much more broadly distributed. ACL has been reported in 160/183 (87.4%) of the municipalities with records for at least one of the six incriminated or suspected sand fly vector species, while there are no records of any of these sand fly species in 318/478 (66.5%) municipalities with ACL. Conclusions: The maps produced in this work provide basic data on the distribution of the six incriminated or suspected sand fly vectors of ACL in the state of Sao Paulo, and highlight the complex and geographically heterogeneous pattern of ACL transmission in the region. Further studies are required to clarify the role of each of the six suspected sand fly vector species in different regions of the state of Sao Paulo, especially in the majority of municipalities where ACL is present but sand fly vectors have not yet been identified.

Concordant Phylogeographies of 2 Malaria Vectors Attest to Common Spatial and Demographic Histories

The phylogeography of South American lineages is a topic of heated debate. Although a single process is unlikely to describe entire ecosystems, related species, which incur similar habitat limitations, can inform the history for a subsection of assemblages. We compared the phylogeographic patterns of the cytochrome oxidase I marker from Anopheles triannulatus (N = 72) and previous results for A. darlingi (N = 126) in a broad portion of their South American distributions. Both species share similar population subdivisions, with aggregations northeast of the Amazon River, in southern coastal Brazil and 2 regions in central Brazil. The average (ST) between these groups was 0.39 for A. triannulatus. Populations northeast of the Amazon and in southeastern Brazil are generally reciprocally monophyletic to the remaining groups. Based on these initial analyses, we constructed the a priori hypothesis that the Amazon and regions of high declivity pose geographic barriers to dispersal in these taxa. Mantel tests confirmed that these areas block gene flow for more than 1000 km for both species. The efficacy of these impediments was tested using landscape genetics, which could not reject our a priori hypothesis but did reject simpler scenarios. Results form summary statistics and phylogenetics suggest that both lineages originated in central Amazonia (south of the Amazon River) during the late Pleistocene (579 000 years ago) and that they followed the same paths of expansion into their contemporary distributions. These results may have implications for other species sharing similar ecological limitations but probably are not applicable as a general paradigm of Neotropical biogeography.

Potential vectors and hosts of rickettsia spp: epidemiological studies in the Vale do Paraiba, state of Rio de Janeiro/Brazil

FAPESP

CD8(+) T cell adjuvant effects of Salmonella FliCd flagellin in live vaccine vectors or as purified protein

Salmonella flagellin, the flagellum structural subunit, has received particular interest as a vaccine adjuvant conferring enhanced immunogenity to soluble proteins or peptides, both for activation of antibody and cellular immune responses. In the present study, we evaluated the Salmonella enterica FliCd flagellin as a T cell vaccine adjuvant using as model the 9-mer (SYVPSAEQI) synthetic H2(d)-restricted CD8(+) T cell-specific epitope (CS(280-288)) derived from the Plasmodium yoelii circumsporozoite (G) protein. The FliCd adjuvant effects were determined under two different conditions: (i) as recombinant flagella, expressed by orally delivered live S. Dublin vaccine strains expressing the target CS(280-288) peptide fused at the central hypervariable domain, and (ii) as purified protein in acellular vaccines in which flagellin was administered to mice either as a recombinant protein fused or admixed with the target CS(280-288) peptide. The results showed that CS(280-288)-specific cytotoxic CD8(+) T cells were primed when BALB/c mice were orally inoculated with the expressing the CS280-288 epitope S. Dublin vaccine strain. In contrast, mice immunized with purified FliCd admixed with the CS280-288 peptide and, to a lesser extent, fused with the target peptide developed specific cytotoxic CD8(+) T cell responses without the need of a heterologous booster immunization. The CD8(+) T cell adjuvant effects of flagellin, either fused or not with the target peptide, correlated with the in vivo activation of CD11c(+) dendritic cells. Taken together, the present results demonstrate that Salmonella flagellins are flexible adjuvant and induce adaptative immune responses when administered by different routes or vaccine formulations. (C) 2009 Elsevier Ltd. All rights reserved.

Towards improving cluster-based feature selection with a simplified silhouette filter

This paper proposes a filter-based algorithm for feature selection. The filter is based on the partitioning of the set of features into clusters. The number of clusters, and consequently the cardinality of the subset of selected features, is automatically estimated from data. The computational complexity of the proposed algorithm is also investigated. A variant of this filter that considers feature-class correlations is also proposed for classification problems. Empirical results involving ten datasets illustrate the performance of the developed algorithm, which in general has obtained competitive results in terms of classification accuracy when compared to state of the art algorithms that find clusters of features. We show that, if computational efficiency is an important issue, then the proposed filter May be preferred over their counterparts, thus becoming eligible to join a pool of feature selection algorithms to be used in practice. As an additional contribution of this work, a theoretical framework is used to formally analyze some properties of feature selection methods that rely on finding clusters of features. (C) 2011 Elsevier Inc. All rights reserved.

An investigation into feature construction to assist word sense disambiguation

Identifying the correct sense of a word in context is crucial for many tasks in natural language processing (machine translation is an example). State-of-the art methods for Word Sense Disambiguation (WSD) build models using hand-crafted features that usually capturing shallow linguistic information. Complex background knowledge, such as semantic relationships, are typically either not used, or used in specialised manner, due to the limitations of the feature-based modelling techniques used. On the other hand, empirical results from the use of Inductive Logic Programming (ILP) systems have repeatedly shown that they can use diverse sources of background knowledge when constructing models. In this paper, we investigate whether this ability of ILP systems could be used to improve the predictive accuracy of models for WSD. Specifically, we examine the use of a general-purpose ILP system as a method to construct a set of features using semantic, syntactic and lexical information. This feature-set is then used by a common modelling technique in the field (a support vector machine) to construct a classifier for predicting the sense of a word. In our investigation we examine one-shot and incremental approaches to feature-set construction applied to monolingual and bilingual WSD tasks. The monolingual tasks use 32 verbs and 85 verbs and nouns (in English) from the SENSEVAL-3 and SemEval-2007 benchmarks; while the bilingual WSD task consists of 7 highly ambiguous verbs in translating from English to Portuguese. The results are encouraging: the ILP-assisted models show substantial improvements over those that simply use shallow features. In addition, incremental feature-set construction appears to identify smaller and better sets of features. Taken together, the results suggest that the use of ILP with diverse sources of background knowledge provide a way for making substantial progress in the field of WSD.

Interactive Vector Field Feature Identification

We introduce a flexible technique for interactive exploration of vector field data through classification derived from user-specified feature templates. Our method is founded on the observation that, while similar features within the vector field may be spatially disparate, they share similar neighborhood characteristics. Users generate feature-based visualizations by interactively highlighting well-accepted and domain specific representative feature points. Feature exploration begins with the computation of attributes that describe the neighborhood of each sample within the input vector field. Compilation of these attributes forms a representation of the vector field samples in the attribute space. We project the attribute points onto the canonical 2D plane to enable interactive exploration of the vector field using a painting interface. The projection encodes the similarities between vector field points within the distances computed between their associated attribute points. The proposed method is performed at interactive rates for enhanced user experience and is completely flexible as showcased by the simultaneous identification of diverse feature types.