Multiscale Fractal Descriptors and Polynomial Classifier for Partial Pixels Identification in Regions of Interest of Mammographic Images

Computer systems are used to support breast cancer diagnosis, with decisions taken from measurements carried out in regions of interest (ROIs). We show that support decisions obtained from square or rectangular ROIs can to include background regions with different behavior of healthy or diseased tissues. In this study, the background regions were identified as Partial Pixels (PP), obtained with a multilevel method of segmentation based on maximum entropy. The behaviors of healthy, diseased and partial tissues were quantified by fractal dimension and multiscale lacunarity, calculated through signatures of textures. The separability of groups was achieved using a polynomial classifier. The polynomials have powerful approximation properties as classifiers to treat characteristics linearly separable or not. This proposed method allowed quantifying the ROIs investigated and demonstrated that different behaviors are obtained, with distinctions of 90% for images obtained in the Cranio-caudal (CC) and Mediolateral Oblique (MLO) views.

Dependence of anuran diversity on environmental descriptors in farmland ponds

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The role of spatial and temporal descriptors for neotropical tadpole communities in southern Brazil

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Integrated biomarker responses as environmental status descriptors of a coastal zone (São Paulo, Brazil)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Developing descriptors to predict mechanical properties of nanotubes

Descriptors and quantitative structure property relationships (QSPR) were investigated for mechanical property prediction of carbon nanotubes (CNTs). 78 molecular dynamics (MD) simulations were carried out, and 20 descriptors were calculated to build quantitative structure property relationships (QSPRs) for Young's modulus and Poisson's ratio in two separate analyses: vacancy only and vacancy plus methyl functionalization. In the first analysis, C N2/CT (number of non-sp2 hybridized carbons per the total carbons) and chiral angle were identified as critical descriptors for both Young's modulus and Poisson's ratio. Further analysis and literature findings indicate the effect of chiral angle is negligible at larger CNT radii for both properties. Raman spectroscopy can be used to measure CN2/C T, providing a direct link between experimental and computational results. Poisson's ratio approaches two different limiting values as CNT radii increases: 0.23-0.25 for chiral and armchair CNTs and 0.10 for zigzag CNTs (surface defects <3%). In the second analysis, the critical descriptors were CN2/CT, chiral angle, and MN/CT (number of methyl groups per total carbons). These results imply new types of defects can be represented as a new descriptor in QSPR models. Finally, results are qualified and quantified against experimental data. © 2013 American Chemical Society.

Quantitative descriptors and their direct and indirect effects on corn yield

The objective of this study was to evaluate the direct and indirect effects of ten quantitative descriptors of agronomic importance in productivity of 25 maize hybrids and their respective influences of heritability. The experiment in randomized blocks with four replications, was conducted in 2010/2011 crop in a soil under humid subtropical climate. The quantitative descriptors were: ear length, ear diameter, cob diameter, number of rows of grains, stem diameter, plant height, ear height, weight of 100 grains, grain weight per ear and number of grains per ear. The grain weight per ear and ear length showed high correlation with grain yield, and the descriptors with the highest potential for selecting superior genotypes and showing high heritability.

HTS and HTSn: New shape descriptors based on Hough transform statistics

With the widespread proliferation of computers, many human activities entail the use of automatic image analysis. The basic features used for image analysis include color, texture, and shape. In this paper, we propose a new shape description method, called Hough Transform Statistics (HTS), which uses statistics from the Hough space to characterize the shape of objects or regions in digital images. A modified version of this method, called Hough Transform Statistics neighborhood (HTSn), is also presented. Experiments carried out on three popular public image databases showed that the HTS and HTSn descriptors are robust, since they presented precision-recall results much better than several other well-known shape description methods. When compared to Beam Angle Statistics (BAS) method, a shape description method that inspired their development, both the HTS and the HTSn methods presented inferior results regarding the precision-recall criterion, but superior results in the processing time and multiscale separability criteria. The linear complexity of the HTS and the HTSn algorithms, in contrast to BAS, make them more appropriate for shape analysis in high-resolution image retrieval tasks when very large databases are used, which are very common nowadays. (C) 2014 Elsevier Inc. All rights reserved.

Automatic classification of prostate stromal tissue in histological images using Haralick descriptors and Local Binary Patterns

In this paper we presente a classification system that uses a combination of texture features from stromal regions: Haralick features and Local Binary Patterns (LBP) in wavelet domain. The system has five steps for classification of the tissues. First, the stromal regions were detected and extracted using segmentation techniques based on thresholding and RGB colour space. Second, the Wavelet decomposition was applied in the extracted regions to obtain the Wavelet coefficients. Third, the Haralick and LBP features were extracted from the coefficients. Fourth, relevant features were selected using the ANOVA statistical method. The classication (fifth step) was performed with Radial Basis Function (RBF) networks. The system was tested in 105 prostate images, which were divided into three groups of 35 images: normal, hyperplastic and cancerous. The system performance was evaluated using the area under the ROC curve and resulted in 0.98 for normal versus cancer, 0.95 for hyperplasia versus cancer and 0.96 for normal versus hyperplasia. Our results suggest that texture features can be used as discriminators for stromal tissues prostate images. Furthermore, the system was effective to classify prostate images, specially the hyperplastic class which is the most difficult type in diagnosis and prognosis.

Fractal descriptors for discrimination of microscopy images of plant leaves

This study proposes the application of fractal descriptors method to the discrimination of microscopy images of plant leaves. Fractal descriptors have demonstrated to be a powerful discriminative method in image analysis, mainly for the discrimination of natural objects. In fact, these descriptors express the spatial arrangement of pixels inside the texture under different scales and such arrangements are directly related to physical properties inherent to the material depicted in the image. Here, we employ the Bouligand-Minkowski descriptors. These are obtained by the dilation of a surface mapping the gray-level texture. The classification of the microscopy images is performed by the well-known Support Vector Machine (SVM) method and we compare the success rate with other literature texture analysis methods. The proposed method achieved a correctness rate of 89%, while the second best solution, the Co-occurrence descriptors, yielded only 78%. This clear advantage of fractal descriptors demonstrates the potential of such approach in the analysis of the plant microscopy images.

Genetic divergence among maize hybrids by morphological descriptors

Two experiments with 25 maize commercial hybrids were carried out in a direct sowing system in Southern Brazil in the harvests of 2009/2010 and 2010/2011. Quantitative descriptors were used with the objective of determining the genetic divergence and the relative contributions of traits among hybrids for extraction of inbred lines. This study was carried out in Oxisol soil using a randomized block design with four replicates. Data were subjected to combined analysis of variance, and based on the multivariate analyses, Tocher and average linkage (UPGMA) cluster analyses, based on generalized distance of Mahalanobis, to quantify divergence in addition to Singh criterion to validate trait with the most contribution. The multivariate methods were consistent with each other, and the weight of 100 grains was the trait that contributed most to the divergence and had similar behavior in grain yield between hybrids in both years. Furthermore, this descriptor representing significant genetic variability for crossings and lines extraction to hybridization between BM 3061, ATL 200 and P 30B39 Y.

Automatic method to classify images based on multiscale fractal descriptors and paraconsistent logic

In this study is presented an automatic method to classify images from fractal descriptors as decision rules, such as multiscale fractal dimension and lacunarity. The proposed methodology was divided in three steps: quantification of the regions of interest with fractal dimension and lacunarity, techniques under a multiscale approach; definition of reference patterns, which are the limits of each studied group; and, classification of each group, considering the combination of the reference patterns with signals maximization (an approach commonly considered in paraconsistent logic). The proposed method was used to classify histological prostatic images, aiming the diagnostic of prostate cancer. The accuracy levels were important, overcoming those obtained with Support Vector Machine (SVM) and Bestfirst Decicion Tree (BFTree) classifiers. The proposed approach allows recognize and classify patterns, offering the advantage of giving comprehensive results to the specialists.

Plant identification based on leaf midrib cross-section images using fractal descriptors

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Hematological analysis of Micropogonias Furnieri, Desmarest, 1823, Scianidae, from two estuaries of Baixada Santista, São paulo Brazil

Alterações hematológicas em peixes são consideradas uma importante ferramenta para avaliar processos patológicos decorrentes da exposição a poluentes ambientais. Micropogonias furnieri (Desmarest, 1823) (corvina) é comumente encontrada em regiões estuarinas e eventualmente está exposta a inúmeros contaminantes. No presente estudo foi avaliado o quadro hematológico de indivíduos de M. furnieri coletados na Baixada Santista: o Sistema Estuarino de Santos, considerado poluído, e o estuário do Rio Itanhaém (controle). Foram avaliados o número de Eritrócitos (Er), o Hematócrito (Ht), a taxa de Hemoglobina (Hb), o Volume Corpuscular Médio (VCM) e a Concentração de Hemoglobina Corpuscular Média (CHCM). Nos peixes coletados no Sistema Estuarino de Santos, os níveis de Ht foram significativamente menores, enquanto os níveis de CHCM e Hb foram significativamente mais altos, indicando que os prováveis efeitos estejam atribuídos aos diferentes níveis de contaminação encontrados nos estuários.

Natural infection of gastrointestinal nematodes in long-nosed armadillos Dasypus novemcinctus Linnaeus, 1758 from Pantanal wetlands, Aquidauana sub-region, Mato Grosso do Sul State, with the description of Hadrostrongylus speciosum n. gen. et n. sp (Molineidae : Anoplostrongylinae)

This study evaluated the gastrointestinal helminth fauna of long-nosed armadillos, Dasypus novemcinctus, from the Pantanal wetlands, Aquidauana sub-region, Aquidauana County, Mato Grosso do Sul State, Brazil. Thirteen species of nematodes, comprising seven genera and four families, were recovered from their gastrointestinal tracts. The following descriptors of infection were determined: prevalence, variation of intensity, average intensity and abundance. Hadrostrongylus speciosum n. gen. et n. sp. is first described here. (c) 2006 Published by Elsevier B.V.

Helminthological screening of free-ranging grey brocket deer Mazama gouazoubira Fischer, 1817 (Cervidae: Odocoileini) from Brazilian Pantanal wetlands, with considerations on Pygarginema verrucosa (Molin, 1860) Kadenatzii, 1948 (Spirocercidae: Ascaropsinae)

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)