Microcalcifications Detection using PFCM and ANN

This work presents a method to detect Microcalcifications in Regions of Interest from digitized mammograms. The method is based mainly on the combination of Image Processing, Pattern Recognition and Artificial Intelligence. The Top-Hat transform is a technique based on mathematical morphology operations that, in this work is used to perform contrast enhancement of microcalcifications in the region of interest. In order to find more or less homogeneous regions in the image, we apply a novel image sub-segmentation technique based on Possibilistic Fuzzy c-Means clustering algorithm. From the original region of interest we extract two window-based features, Mean and Deviation Standard, which will be used in a classifier based on a Artificial Neural Network in order to identify microcalcifications. Our results show that the proposed method is a good alternative in the stage of microcalcifications detection, because this stage is an important part of the early Breast Cancer detection

Usando Kinect como sensor para una pulverización inteligente.

Este trabajo esta orientado a resolver el problema de la caracterización de la copa de arboles frutales para la aplicacion localizada de fitosanitarios. Esta propuesta utiliza un mapa de profundidad (Depth image) y una imagen RGB combinadas (RGB-D), proporcionados por el sensor Kinect de Microsoft, para aplicar pesticidas de forma localizada. A través del mapa de profundidad se puede estimar la densidad de la copa y a partir de esta información determinar qué boquillas se deben abrir en cada momento. Se desarrollaron algoritmos implementados en Matlab que permiten además de la adquisición de las imágenes RGB-D, aplicar plaguicidas sólo a hojas y/o frutos según se desee. Estos algoritmos fueron implementados en un software que se comunica con el entorno de desarrollo "Kinect Windows SDK", encargado de extraer las imágenes desde el sensor Kinect. Por otra parte, para identificar hojas, se implementaron algoritmos de clasificación e identificación. Los algoritmos de clasificación utilizados fueron "Fuzzy C-Means con Gustafson Kessel" (FCM-GK) y "K-Means". Los centroides o prototipos de cada clase generados por FCM-GK fueron usados como semilla para K-Means, para acelerar la convergencia del algoritmo y mantener la coherencia temporal en los grupos generados por K-Means. Los algoritmos de clasificación fueron aplicados sobre las imágenes transformadas al espacio de color L*a*b*; específicamente se emplearon los canales a*, b* (canales cromáticos) con el fin de reducir el efecto de la luz sobre los colores. Los algoritmos de clasificación fueron configurados para buscar cuatro grupos: hojas, porosidad, frutas y tronco. Una vez que el clasificador genera los prototipos de los grupos, un clasificador denominado Máquina de Soporte Vectorial, que utiliza como núcleo una función Gaussiana base radial, identifica la clase de interés (hojas). La combinación de estos algoritmos ha mostrado bajos errores de clasificación, rendimiento del 4% de error en la identificación de hojas. Además, estos algoritmos de procesamiento de hasta 8.4 imágenes por segundo, lo que permite su aplicación en tiempo real. Los resultados demuestran la viabilidad de utilizar el sensor "Kinect" para determinar dónde y cuándo aplicar pesticidas. Por otra parte, también muestran que existen limitaciones en su uso, impuesta por las condiciones de luz. En otras palabras, es posible usar "Kinect" en exteriores, pero durante días nublados, temprano en la mañana o en la noche con iluminación artificial, o añadiendo un parasol en condiciones de luz intensa.

Aplicación de técnicas de inteligencia artificial para contribuir en la detección de microcalcificaciones en mamografía digitalizada

A nivel mundial, el cáncer de mama es el tipo de cáncer más frecuente además de una de las principales causas de muerte entre la población femenina. Actualmente, el método más eficaz para detectar lesiones mamarias en una etapa temprana es la mamografía. Ésta contribuye decisivamente al diagnóstico precoz de esta enfermedad que, si se detecta a tiempo, tiene una probabilidad de curación muy alta. Uno de los principales y más frecuentes hallazgos en una mamografía, son las microcalcificaciones, las cuales son consideradas como un indicador importante de cáncer de mama. En el momento de analizar las mamografías, factores como la capacidad de visualización, la fatiga o la experiencia profesional del especialista radiólogo hacen que el riesgo de omitir ciertas lesiones presentes se vea incrementado. Para disminuir dicho riesgo es importante contar con diferentes alternativas como por ejemplo, una segunda opinión por otro especialista o un doble análisis por el mismo. En la primera opción se eleva el coste y en ambas se prolonga el tiempo del diagnóstico. Esto supone una gran motivación para el desarrollo de sistemas de apoyo o asistencia en la toma de decisiones. En este trabajo de tesis se propone, se desarrolla y se justifica un sistema capaz de detectar microcalcificaciones en regiones de interés extraídas de mamografías digitalizadas, para contribuir a la detección temprana del cáncer demama. Dicho sistema estará basado en técnicas de procesamiento de imagen digital, de reconocimiento de patrones y de inteligencia artificial. Para su desarrollo, se tienen en cuenta las siguientes consideraciones: 1. Con el objetivo de entrenar y probar el sistema propuesto, se creará una base de datos de imágenes, las cuales pertenecen a regiones de interés extraídas de mamografías digitalizadas. 2. Se propone la aplicación de la transformada Top-Hat, una técnica de procesamiento digital de imagen basada en operaciones de morfología matemática. La finalidad de aplicar esta técnica es la de mejorar el contraste entre las microcalcificaciones y el tejido presente en la imagen. 3. Se propone un algoritmo novel llamado sub-segmentación, el cual está basado en técnicas de reconocimiento de patrones aplicando un algoritmo de agrupamiento no supervisado, el PFCM (Possibilistic Fuzzy c-Means). El objetivo es encontrar las regiones correspondientes a las microcalcificaciones y diferenciarlas del tejido sano. Además, con la finalidad de mostrar las ventajas y desventajas del algoritmo propuesto, éste es comparado con dos algoritmos del mismo tipo: el k-means y el FCM (Fuzzy c-Means). Por otro lado, es importante destacar que en este trabajo por primera vez la sub-segmentación es utilizada para detectar regiones pertenecientes a microcalcificaciones en imágenes de mamografía. 4. Finalmente, se propone el uso de un clasificador basado en una red neuronal artificial, específicamente un MLP (Multi-layer Perceptron). El propósito del clasificador es discriminar de manera binaria los patrones creados a partir de la intensidad de niveles de gris de la imagen original. Dicha clasificación distingue entre microcalcificación y tejido sano. ABSTRACT Breast cancer is one of the leading causes of women mortality in the world and its early detection continues being a key piece to improve the prognosis and survival. Currently, the most reliable and practical method for early detection of breast cancer is mammography.The presence of microcalcifications has been considered as a very important indicator ofmalignant types of breast cancer and its detection and classification are important to prevent and treat the disease. However, the detection and classification of microcalcifications continue being a hard work due to that, in mammograms there is a poor contrast between microcalcifications and the tissue around them. Factors such as visualization, tiredness or insufficient experience of the specialist increase the risk of omit some present lesions. To reduce this risk, is important to have alternatives such as a second opinion or a double analysis for the same specialist. In the first option, the cost increases and diagnosis time also increases for both of them. This is the reason why there is a great motivation for development of help systems or assistance in the decision making process. This work presents, develops and justifies a system for the detection of microcalcifications in regions of interest extracted fromdigitizedmammographies to contribute to the early detection of breast cancer. This systemis based on image processing techniques, pattern recognition and artificial intelligence. For system development the following features are considered: With the aim of training and testing the system, an images database is created, belonging to a region of interest extracted from digitized mammograms. The application of the top-hat transformis proposed. This image processing technique is based on mathematical morphology operations. The aim of this technique is to improve the contrast betweenmicrocalcifications and tissue present in the image. A novel algorithm called sub-segmentation is proposed. The sub-segmentation is based on pattern recognition techniques applying a non-supervised clustering algorithm known as Possibilistic Fuzzy c-Means (PFCM). The aim is to find regions corresponding to the microcalcifications and distinguish them from the healthy tissue. Furthermore,with the aim of showing themain advantages and disadvantages this is compared with two algorithms of same type: the k-means and the fuzzy c-means (FCM). On the other hand, it is important to highlight in this work for the first time the sub-segmentation is used for microcalcifications detection. Finally, a classifier based on an artificial neural network such as Multi-layer Perceptron is used. The purpose of this classifier is to discriminate froma binary perspective the patterns built from gray level intensity of the original image. This classification distinguishes between microcalcifications and healthy tissue.

Identification of pore spaces in 3D CT soil images using a PFCM partitional clustering

Recent advances in non-destructive imaging techniques, such as X-ray computed tomography (CT), make it possible to analyse pore space features from the direct visualisation from soil structures. A quantitative characterisation of the three-dimensional solid-pore architecture is important to understand soil mechanics, as they relate to the control of biological, chemical, and physical processes across scales. This analysis technique therefore offers an opportunity to better interpret soil strata, as new and relevant information can be obtained. In this work, we propose an approach to automatically identify the pore structure of a set of 200-2D images that represent slices of an original 3D CT image of a soil sample, which can be accomplished through non-linear enhancement of the pixel grey levels and an image segmentation based on a PFCM (Possibilistic Fuzzy C-Means) algorithm. Once the solids and pore spaces have been identified, the set of 200-2D images is then used to reconstruct an approximation of the soil sample by projecting only the pore spaces. This reconstruction shows the structure of the soil and its pores, which become more bounded, less bounded, or unbounded with changes in depth. If the soil sample image quality is sufficiently favourable in terms of contrast, noise and sharpness, the pore identification is less complicated, and the PFCM clustering algorithm can be used without additional processing; otherwise, images require pre-processing before using this algorithm. Promising results were obtained with four soil samples, the first of which was used to show the algorithm validity and the additional three were used to demonstrate the robustness of our proposal. The methodology we present here can better detect the solid soil and pore spaces on CT images, enabling the generation of better 2D?3D representations of pore structures from segmented 2D images.

Automatic Abdominal Aortic Aneurysm segmentation in MR images

Abdominal Aortic Aneurism is a disease related to a weakening in the aortic wall that can cause a break in the aorta and the death. The detection of an unusual dilatation of a section of the aorta is an indicative of this disease. However, it is difficult to diagnose because it is necessary image diagnosis using computed tomography or magnetic resonance. An automatic diagnosis system would allow to analyze abdominal magnetic resonance images and to warn doctors if any anomaly is detected. We focus our research in magnetic resonance images because of the absence of ionizing radiation. Although there are proposals to identify this disease in magnetic resonance images, they need an intervention from clinicians to be precise and some of them are computationally hard. In this paper we develop a novel approach to analyze magnetic resonance abdominal images and detect the lumen and the aortic wall. The method combines different algorithms in two stages to improve the detection and the segmentation so it can be applied to similar problems with other type of images or structures. In a first stage, we use a spatial fuzzy C-means algorithm with morphological image analysis to detect and segment the lumen; and subsequently, in a second stage, we apply a graph cut algorithm to segment the aortic wall. The obtained results in the analyzed images are pretty successful obtaining an average of 79% of overlapping between the automatic segmentation provided by our method and the aortic wall identified by a medical specialist. The main impact of the proposed method is that it works in a completely automatic way with a low computational cost, which is of great significance for any expert and intelligent system.

Magnetic charachterization of surface sediments in the South Atlantic

Surface sediment samples representative for the tropical and subtropical South Atlantic (15°N to 40°S) were investigated by isothermal magnetic methods to delineate magnetic mineral distribution patterns and to identify their predominant Holocene climatic and oceanographic controls. Individual parameters reveal distinct, yet frequently overlapping, regional sedimentation characteristics. A probabilistic ('fuzzy c-means') cluster analysis was applied to five concentration independent magnetic properties assessing magnetite to hematite ratios and diagnostic of bulk and fine-particle magnetite grain size and coercivity spectra. The resultant 10 cluster structures establish an oceanwide magnetic sediment classification scheme tracing the major terrigenous eolian and fluvial fluxes, authigenic biogenic magnetite accumulation in high-productivity areas, transport by ocean current systems, and effects of bottom water velocity on depositional regimes. Distinct dissimilarities in magnetic mineral inventories between the eastern and western basins of the South Atlantic reflect prominent contrasts of both oceanic and continental influences.

X-ray diffraction analysis, binocular component analysis and radiocarbon dating of sediment cores from the NW Iberian shelf system

Based on a well-established stratigraphic framework and 47 AMS-14C dated sediment cores, the distribution of facies types on the NW Iberian margin is analysed in response to the last deglacial sea-level rise, thus providing a case study on the sedimentary evolution of a high-energy, low-accumulation shelf system. Altogether, four main types of sedimentary facies are defined. (1) A gravel-dominated facies occurs mostly as time-transgressive ravinement beds, which initially developed as shoreface and storm deposits in shallow waters on the outer shelf during the last sea-level lowstand; (2) A widespread, time-transgressive mixed siliceous/biogenic-carbonaceous sand facies indicates areas of moderate hydrodynamic regimes, high contribution of reworked shelf material, and fluvial supply to the shelf; (3) A glaucony-containing sand facies in a stationary position on the outer shelf formed mostly during the last-glacial sea-level rise by reworking of older deposits as well as authigenic mineral formation; and (4) A mud facies is mostly restricted to confined Holocene fine-grained depocentres, which are located in mid-shelf position. The observed spatial and temporal distribution of these facies types on the high-energy, low-accumulation NW Iberian shelf was essentially controlled by the local interplay of sediment supply, shelf morphology, and strength of the hydrodynamic system. These patterns are in contrast to high-accumulation systems where extensive sediment supply is the dominant factor on the facies distribution. This study emphasises the importance of large-scale erosion and material recycling on the sedimentary buildup during the deglacial drowning of the shelf. The presence of a homogenous and up to 15-m thick transgressive cover above a lag horizon contradicts the common assumption of sparse and laterally confined sediment accumulation on high-energy shelf systems during deglacial sea-level rise. In contrast to this extensive sand cover, laterally very confined and maximal 4-m thin mud depocentres developed during the Holocene sea-level highstand. This restricted formation of fine-grained depocentres was related to the combination of: (1) frequently occurring high-energy hydrodynamic conditions; (2) low overall terrigenous input by the adjacent rivers; and (3) the large distance of the Galicia Mud Belt to its main sediment supplier.

Mineralogical, geochemical and magnetic signatures of surface sediments from the Canadian Beaufort Shelf and Amundsen Gulf (Canadian Arctic)

Mineralogical, geochemical, magnetic, and siliciclastic grain-size signatures of 34 surface sediment samples from the Mackenzie-Beaufort Sea Slope and Amundsen Gulf were studied in order to better constrain the redox status, detrital particle provenance, and sediment dynamics in the western Canadian Arctic. Redox-sensitive elements (Mn, Fe, V, Cr, Zn) indicate that modern sedimentary deposition within the Mackenzie-Beaufort Sea Slope and Amundsen Gulf took place under oxic bottom-water conditions, with more turbulent mixing conditions and thus a well-oxygenated water column prevailing within the Amundsen Gulf. The analytical data obtained, combined with multivariate statistical (notably, principal component and fuzzy c-means clustering analyses) and spatial analyses, allowed the division of the study area into four provinces with distinct sedimentary compositions: (1) the Mackenzie Trough-Canadian Beaufort Shelf with high phyllosilicate-Fe oxide-magnetite and Al-K-Ti-Fe-Cr-V-Zn-P contents; (2) Southwestern Banks Island, characterized by high dolomite-K-feldspar and Ca-Mg-LOI contents; (3) the Central Amundsen Gulf, a transitional zone typified by intermediate phyllosilicate-magnetite-K-feldspar-dolomite and Al-K-Ti-Fe-Mn-V-Zn-Sr-Ca-Mg-LOI contents; and (4) mud volcanoes on the Canadian Beaufort Shelf distinguished by poorly sorted coarse-silt with high quartz-plagioclase-authigenic carbonate and Si-Zr contents, as well as high magnetic susceptibility. Our results also confirm that the present-day sedimentary dynamics on the Canadian Beaufort Shelf is mainly controlled by sediment supply from the Mackenzie River. Overall, these insights provide a basis for future studies using mineralogical, geochemical, and magnetic signatures of Canadian Arctic sediments in order to reconstruct past variations in sediment inputs and transport pathways related to late Quaternary climate and oceanographic changes.

Enviromagnetic, major element, and grain-size analyses of surface sediment samples along the continental margin between East Brazil and Patagonia

Continental margin sediments of SE South America originate from various terrestrial sources, each conveying specific magnetic and element signatures. Here, we aim to identify the sources and transport characteristics of shelf and slope sediments deposited between East Brazil and Patagonia (20°-48°S) using enviromagnetic, major element, and grain-size data. A set of five source-indicative parameters (i.e., chi-fd%, ARM/IRM, S0.3T, SIRM/Fe and Fe/K) of 25 surface samples (16-1805 m water depth) was analyzed by fuzzy c-means clustering and non-linear mapping to depict and unmix sediment-province characteristics. This multivariate approach yields three regionally coherent sediment provinces with petrologically and climatically distinct source regions. The southernmost province is entirely restricted to the slope off the Argentinean Pampas and has been identified as relict Andean-sourced sands with coarse unaltered magnetite. The direct transport to the slope was enabled by Rio Colorado and Rio Negro meltwaters during glacial and deglacial phases of low sea level. The adjacent shelf province consists of coastal loessoidal sands (highest hematite and goethite proportions) delivered from the Argentinean Pampas by wave erosion and westerly winds. The northernmost province includes the Plata mudbelt and Rio Grande Cone. It contains tropically weathered clayey silts from the La Plata Drainage Basin with pronounced proportions of fine magnetite, which were distributed up to ~24° S by the Brazilian Coastal Current and admixed to coarser relict sediments of Pampean loessoidal origin. Grain-size analyses of all samples showed that sediment fractionation during transport and deposition had little impact on magnetic and element source characteristics. This study corroborates the high potential of the chosen approach to access sediment origin in regions with contrasting sediment sources, complex transport dynamics, and large grain-size variability.

Trajetória da gestão de dados na organização: resultado da negociação entre os grupos envolvidos

O dado e a informação passaram a ser vistos como recursos essenciais e ativos preciosos das organizações. Nas últimas décadas, as empresas investiram maciçamente em projetos de Tecnologia da Informação (TI) que visavam ter uma melhor gestão dos seus dados com o propósito de ganhar vantagem competitiva. Apesar de ter evoluído, trata-se de um assunto não totalmente resolvido: as organizações continuam em busca de soluções que, efetivamente, organizem seus dados de maneira íntegra e garantam seu crescimento sustentável. Esta pesquisa pretendeu investigar, sob a ótica dos atores envolvidos nas grandes projetos de organização, integração, gestão, governança dos dados na empresa, o efeito que o histórico dessas iniciativas proporcionou em uma instituição de grande porte nacional. A partir da análise iterativa do ciclo de negociação dos grupos constituídos pelos atores envolvidos, além de tentar traçar a trajetória em que se deu essa história de dados na empresa, também se pretendeu investigar a dinâmica presente nas iniciativas e o quanto ela, por meio dos stakeholders envolvidos, influencia nas iniciativas atualmente existentes na organização. Para suportar esse objetivo, o trabalho se baseou nas categorias conceituais da Abordagem Multinível (DINIZ; POZZEBON; JAYO, 2009; POZZEBON; DINIZ, 2012) – Contexto, Processo e Conteúdo, identificando os Grupos Sociais Relevantes que interagiram no processo de negociação para implantação da tecnologia, na busca pela melhor solução de dados que atendesse à empresa em um mercado em constante movimento e na tomada de decisões que direcionam a prática deste processo. Tratou-se de um estudo exploratório realizado com entrevistas semiestruturadas com gestores de TI e negócios envolvidos que tiveram alguma interação ou influência com algumas iniciativas na empresa. A análise dos resultados revela aspectos que poderão contribuir de forma a deixar cada vez mais evidente a interferência dos stakeholders nas soluções de tecnologia e o quanto isso pode ser uma ameaça para o uso efetivo do dado como um ativo da empresa e, assim, garantir sua sobrevivência e seu desenvolvimento, caso os incentivos não estejam alinhados.

Algoritmos de agrupamento aplicados a dados de expressão gênica de câncer: um estudo comparativo

The use of clustering methods for the discovery of cancer subtypes has drawn a great deal of attention in the scientific community. While bioinformaticians have proposed new clustering methods that take advantage of characteristics of the gene expression data, the medical community has a preference for using classic clustering methods. There have been no studies thus far performing a large-scale evaluation of different clustering methods in this context. This work presents the first large-scale analysis of seven different clustering methods and four proximity measures for the analysis of 35 cancer gene expression data sets. Results reveal that the finite mixture of Gaussians, followed closely by k-means, exhibited the best performance in terms of recovering the true structure of the data sets. These methods also exhibited, on average, the smallest difference between the actual number of classes in the data sets and the best number of clusters as indicated by our validation criteria. Furthermore, hierarchical methods, which have been widely used by the medical community, exhibited a poorer recovery performance than that of the other methods evaluated. Moreover, as a stable basis for the assessment and comparison of different clustering methods for cancer gene expression data, this study provides a common group of data sets (benchmark data sets) to be shared among researchers and used for comparisons with new methods

On the efficiency of evolutionary fuzzy clustering

This paper tackles the problem of showing that evolutionary algorithms for fuzzy clustering can be more efficient than systematic (i.e. repetitive) approaches when the number of clusters in a data set is unknown. To do so, a fuzzy version of an Evolutionary Algorithm for Clustering (EAC) is introduced. A fuzzy cluster validity criterion and a fuzzy local search algorithm are used instead of their hard counterparts employed by EAC. Theoretical complexity analyses for both the systematic and evolutionary algorithms under interest are provided. Examples with computational experiments and statistical analyses are also presented.

A importância da identificação botânica nos inventários florestais: o exemplo do "tauari" (Couratari spp. e Cariniana spp. - Lecythidaceae) em duas áreas manejadas no estado do Pará

O nome vulgar adotado nos inventários florestais tem agrupado espécies distintas. Para exemplificar este problema, foram avaliadas as identificações de indivíduos comercialmente determinados como "tauari" em inventários de duas áreas manejadas de 100 ha nos pólos madeireiro central e leste do Estado do Pará. Características dendrológicas de cada espécie foram anotadas para diferenciá-las. Dados sobre a distribuição geográfica dessas espécies, as propriedades tecnológicas de sua madeira e a legislação atual para o manejo florestal são discutidos. O inventário feito no pólo madeireiro central registrou 112 indivíduos de "tauari" nominados como Couratari guianensis, e seis indivíduos de "tauari-cachimbo" determinados como Couratari sp. Depois de uma revisão botânica com material coletado de cada árvore, foi constatado que os indivíduos determinados como Couratari guianensis agrupavam três espécies: Couratari guianensis, C. oblongifolia e C. stellata, esta última com maior densidade relativa. O que antes constava como Couratari sp. agrupava as espécies Cariniana micrantha e Cariniana decandra. No pólo leste, o inventário contava 33 indivíduos, listados como "tauari" ou Couratari guianensis. Para estes, a identificação botânica mostrou o agrupamento de duas espécies: C. guianensis com maior densidade relativa e C. oblongifolia. Fora da área de estudo, foi registrada a ocorrência de C. tauari. Este estudo mostra que é possível separar as espécies utilizando aspectos dendrológicos (folhas, ramos e tronco). O inventário botânico é demonstrado como base para o conhecimento da diversidade e indispensável para assegurar o sucesso dos planos de manejo. No contexto jurídico, o agrupamento inviabiliza o cumprimento das leis brasileiras referentes ao manejo.

Alunos em risco na fluência da leitura: o uso da monitorização com base no currículo no contexto de um modelo de resposta à intervenção

Dissertação de mestrado em Educação Especial (área de especialização em Dificuldades de Aprendizagem Específicas)

Aggregation invariance in general clustering approaches

General clustering deals with weighted objects and fuzzy memberships. We investigate the group- or object-aggregation-invariance properties possessed by the relevant functionals (effective number of groups or objects, centroids, dispersion, mutual object-group information, etc.). The classical squared Euclidean case can be generalized to non-Euclidean distances, as well as to non-linear transformations of the memberships, yielding the c-means clustering algorithm as well as two presumably new procedures, the convex and pairwise convex clustering. Cluster stability and aggregation-invariance of the optimal memberships associated to the various clustering schemes are examined as well.