Plataforma TI de vigilancia entomológica del Aedes aegypti con colaboración colectiva, Web GIS y mHealth / IT platform for entomological surveillance of Aedes aegypti with crowdsourcing, Web GIS and mHealth / Plataforma de TI para vigilância entomològica de Aedes aegypti com colaboração coletiva, Web GIS e mHealth

RESUMEN El mosquito Aedes aegypti es una especie antropoflica que se ha adaptado a entornos urbanos y es el principal vector de enfermedades como el dengue, la fiebre de Zika, la enfermedad del Chikungunya y la fiebre amarilla, lo que representa una importante carga al sistema de salud, en especial en países tropicales donde es endèmico. Ejercer apropiadamente la vigilancia en salud pública es fundamental para la prevención de estas enfermedades mediante sistemas de información. El propósito de este trabajo es proporcionar una plataforma de tecnologias de la información (TI), integrando tecnologias abiertas Web GIS y mHealth para la vigilancia entomológica del vector a partir de colaboración abierta distribuida para la generación de mapas de infestación. Se realizó un piloto con un grupo focal de 23 estudiantes del curso de epidemiologia, que permitió registrar l20 elementos en 55 reportes en la Universidad de los Llanos para la generación automática de 21 mapas de calor de sintomas, zancudos y criaderos, y un mapa global de infestación. Este trabajo sugiere una perspectiva novedosa de interacción y participación colaborativa de la comunidad con las autoridades de salud soportado por las TI.

ABSTRACT The Aedes aegypti mosquito is an anthropophilic species that has adapted to urban environments and it is the main vector of diseases such as dengue, Zika fever; Chikungunya disease and yellow fever; which represents a significant burden on the health system, especially in tropical countries where it is endemic. Properly exercising public health surveillance is essential for the prevention of these diseases through information systems. The purpose of this work is to provide an information technology (IT) platform, integrating open technologies Web GIS and mHealth for the entomological surveillance ofthe vector; based on crowdsourcing for the generation of infestation maps. A pilot was carried out with a focus group of 23 students from the epidemiology course, which allowed the registration of l20 elements in 55 reports at the Universidad de los Llanos for the automatic generation of 2l heatmaps of symptoms, mosquitoes and breeding sites, and a global infestation map. This work suggests a novel perspective of interaction and collaborative participation of the community with health authorities supported by IT

RESUMO O mosquito Aedes aegypti è uma espècie antropofílica que se adaptou aos ambientes urbanos e è o principal vetor de doenças como dengue, febre Zika, doença Chikungunya e febre amarela, o que representa uma carga significativa para o sistema de saúde, especialmente em países tropicais onde é endêmica. O exercício adequado da vigilância em saúde pública è essencial para a prevenção dessas doenças por meio de sistemas de informação. O objetivo deste trabalho è fornecer uma plataforma de tecnologia da informação (TI), integrando tecnologias abertas Web GIS e mHealth para a vigilância entomológica do vetor com base em uma colaboração aberta distribuída para a geração de mapas de infestação. Um piloto foi realizado com um grupo focal de 23 estudantes do curso de epidemiologia, que permitiu o registro de l20 elementos em 55 relatórios na Universidad de los Llanos para a geração automática de 2l mapas de calor de sintomas, mosquitos e criadouros, e um mapa de infestação global. Este trabalho sugere uma nova perspectiva de interação e participação colaborativa da comunidade com autoridades de saúde apoiadas por TI.

Traffic noise affects foraging behavior and echolocation in the Lesser Bulldog Bat, Noctilio albiventris (Chiroptera: Noctilionidae).

Urban noise, such as that of traffic, can affect the sensory capabilities in animals. Foragers acting optimally are expected to exploit feeding patches depending on the cost/benefit ratio, and some noises can cause increased foraging costs. We hypothesized that traffic noise affects foraging patch quality for aerial-insectivorous bats and predicted that there are measurable differences in their foraging activity and in their echolocation signals between nights with or without traffic noise. We tested these predictions in the Lesser Bulldog Bat, Noctilio albiventris, foraging over aquaculture fishponds, by recording bat activity on nights playing traffic noise and on traffic-sound free control nights. We measured foraging activity by counting the number of search passes and feeding buzzes made by the bats and measured several characteristics of echolocation signals. Foraging activity was higher during noisy nights than during control ones, probably due to the need of more time to obtain information about prey under noisy conditions. When exposed to traffic noise, the bats changed the spectral and temporal characteristics of echolocation signals. We suggest that exposure to traffic noise increases foraging costs for N. albiventris and posit that these bats continue foraging under noisy conditions because they can modulate their echolocation signals to obtain enough information.

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

Clasificación y mapeo automático de coberturas del suelo en imágenes satelitales utilizando Redes Neuronales Convolucionales / Classification and automatic mapping of land covers in satellite images using Convolutional Neural Networks / Classificação e mapeamento automático de coberturas do solo em imagens de satélite usando redes neurais convolucionais

Resumen La clasificación de cobertura del suelo es importante para estudios de cambio climático y monitoreo de servicios ecosistémicos. Los métodos convencionales de clasificación de coberturas se realizan mediante la interpretación visual de imágenes satelitales, lo cual es costoso, dispendioso e impreciso. Implementar métodos computacionales permite generar clasificación de coberturas en imágenes satelitales de manera automática, rápida, precisa y económica. Particularmente, los métodos de aprendizaje automático son técnicas computacionales promisorias para la estimación de cambios de cobertura del suelo. En este trabajo se presenta un método de aprendizaje automático basado en redes neuronales convolucionales de arquitectura tipo ConvNet para la clasificación automática de coberturas del suelo a partir de imágenes Landsat 5 TM. La ConvNet fue entrenada a partir de las anotaciones manuales por medio de interpretación visual sobre las imágenes satelitales con las que los expertos generaron el mapa de cobertura del parque nacional el Tuparro, de los Parques Nacionales Naturales de Colombia. El modelo de validación se realizó con datos de los mapas de coberturas del Amazonas colombiano realizado por el Sistema de Información Ambiental de Colombia. Los resultados obtenidos de la diagonal de la matriz de confusión de la exactitud promedio fue de 83.27% en entrenamiento y 91.02% en validación; para la clasificación en parches entre Bosques, áreas con vegetación herbácea y/o arbustiva, áreas abiertas sin o con poca vegetación y aguas continentales.

Abstract Land cover classification is important for studies of climate change and monitoring of ecosystem services. Conventional coverage classification methods are performed by the visual interpretation of satellite imagery, which is expensive and inaccurate. Implementing computational methods could generate procedures to classify coverage in satellite images automatically, quickly, accurately and economically. Particularly, automatic learning methods are promising computational methods for estimating soil cover changes. In this work we present an automatic learning method based on convolutional neural networks of ConvNet type architecture for the automatic classification of soil coverings from Landsat 5 TM images. The ConvNet was trained from the manual annotations by means of visual interpretation on the satellite images with which the experts generated the map of Tuparro national park, of National Natural Park of Colombia. The validation model was performed with data from the Colombian Amazon cover maps made by the Colombian Environmental Information System. The results obtained from the diagonal of the confusion matrix of the average accuracy were 83.27% in training and 91.02% in validation; for the classification in patches between forests, areas with herbaceous and / or shrub vegetation, open areas with or without vegetation and Inland waters.

Resumo A classificação da cobertura da terra é importante para estudos de mudanças climáticas e monitoramento dos serviços dos ecossistemas. Os métodos convencionais de classificação de cobertura são feitos através da interpretação visual de imagens de satélite, que é caro, dispendioso e impreciso. Implementar métodos computacionais poderia gerar procedimentos de classificação de cobertura em imagenes de satélite de forma automática, rápida, precisa e econômica. Particularmente, métodos de aprendizado de máquina são promissores métodos computacionais para estimar a cobertura do solo mudanças. Neste artigo apresentamos um método de aprendizado de máquina baseado em convolutional neural tipo ConvNet rede de arquitetura para a classificação automática de cobertura do solo a partir de Landsat 5 imagens TM. O ConvNet foi treinado desde anotações manuais através da interpretação visual das imagens de satélite que os especialistas geraram o mapa de cobertura do Parque Nacional Tuparro, Colômbia Parque Nacional Natural. A validação do modelo foi realizada com cobertura de mapa de dados da Amazônia colombiana pelo Sistema de Informação Ambiental da Colômbia. Os resultados da diagonal da matriz de confusão da precisão média foi de 83,27% e Formação e 91,02% na validação; para a classificação em manchas entre florestas, áreas com vegetação herbácea e / ou arbusto, áreas abertas com poucamou nenhuma vegetação águas interiores.

Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent.

With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma.

An unsupervised feature learning framework for basal cell carcinoma image analysis.

OBJECTIVE: The paper addresses the problem of automatic detection of basal cell carcinoma (BCC) in histopathology images. In particular, it proposes a framework to both, learn the image representation in an unsupervised way and visualize discriminative features supported by the learned model. MATERIALS AND METHODS: This paper presents an integrated unsupervised feature learning (UFL) framework for histopathology image analysis that comprises three main stages: (1) local (patch) representation learning using different strategies (sparse autoencoders, reconstruct independent component analysis and topographic independent component analysis (TICA), (2) global (image) representation learning using a bag-of-features representation or a convolutional neural network, and (3) a visual interpretation layer to highlight the most discriminant regions detected by the model. The integrated unsupervised feature learning framework was exhaustively evaluated in a histopathology image dataset for BCC diagnosis. RESULTS: The experimental evaluation produced a classification performance of 98.1%, in terms of the area under receiver-operating-characteristic curve, for the proposed framework outperforming by 7% the state-of-the-art discrete cosine transform patch-based representation. CONCLUSIONS: The proposed UFL-representation-based approach outperforms state-of-the-art methods for BCC detection. Thanks to its visual interpretation layer, the method is able to highlight discriminative tissue regions providing a better diagnosis support. Among the different UFL strategies tested, TICA-learned features exhibited the best performance thanks to its ability to capture low-level invariances, which are inherent to the nature of the problem.

Assessment of algorithms for mitosis detection in breast cancer histopathology images.

The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. However, mitosis counting is laborious, subjective and may suffer from low inter-observer agreement. With the wider acceptance of whole slide images in pathology labs, automatic image analysis has been proposed as a potential solution for these issues. In this paper, the results from the Assessment of Mitosis Detection Algorithms 2013 (AMIDA13) challenge are described. The challenge was based on a data set consisting of 12 training and 11 testing subjects, with more than one thousand annotated mitotic figures by multiple observers. Short descriptions and results from the evaluation of eleven methods are presented. The top performing method has an error rate that is comparable to the inter-observer agreement among pathologists.

Histopathology image representation for automatic analysis: a state-of-the-art review / Representación de imágenes de histopatología utilizada en tareas de análisis automático: estado del arte / Representação de imagens histopatológicas pelo análise automático: revisão do estado da arte

This paper presents a review of the state-of-the-art in histopathology image representation used in automatic image analysis tasks. Automatic analysis of histopathology images is important for building computer-assisted diagnosis tools, automatic image enhancing systems and virtual microscopy systems, among other applications. Histopathology images have a rich mix of visual patterns with particularities that make them difficult to analyze. The paper discusses these particularities, the acquisition process and the challenges found when doing automatic analysis. Second an overview of recent works and methods addressed to deal with visual content representation in different automatic image analysis tasks is presented. Third an overview of applications of image representation methods in several medical domains and tasks is presented. Finally, the paper concludes with current trends of automatic analysis of histopathology images like digital pathology.

Este artículo presenta una revisión del estado del arte en la representación de imágenes de histopatología utilizada en tareas de análisis automático. El análisis de imágenes hispatológicas es importante en la construcción de herramientas para el diagnóstico asistido por computador, sistemas de mejoramiento automático de imágenes y sistemas de microscopía virtual, entre otras aplicaciones. Estas imágenes tienen una gran mezcla de patrones visuales con características particulares que hacen de su análisis una tarea difícil. El artículo discute estas particularidades, el proceso de adquisición y los retos particulares al realizar un análisis automático. En la segunda sección se presenta una revisión de trabajos y métodos recientes enfocados a la representación del contenido visual en diferentes tareas de análisis automático. En tercer lugar, se presenta una visión general de las aplicaciones para los métodos de representación en diferentes dominios médicos. Finalmente el trabajo concluye con las actuales tendencias del análisis automático de imágenes de histopatología como la patología digital.

Este artigo é uma revisão do estado da arte na representação de imagens histopatológicas utilizadas nas tarefas de análise automáticos. O análise de imagens histopatológicas é importante na construção de ferramentas para o diagnóstico assistido por computador, sistemas de melhoramento automático de imagens e sistemas de microscopia virtual. Essas imagens tem uma grande mistura de padrões visuais com caraterísticas particulares, que fazem do análise uma tarefa difícil. O artigo discute essas particularidades, o processo de aquisição, e os desafios particulares no momento de realizar uma análise automático. Na segunda seção se apresenta uma revisão dos trabalhos e métodos recentes, com foco à representação do conteúdo visual em diferentes tarefas de análise automático. Na terceira, se apresenta uma visão geral das aplicações para os métodos de representação em diferentes domínios médicos. Finalmente, o artigo conclui com as atuais tendências do análise automático de imagens histopatológicas como a patologia digital.

Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features.

Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is the mitotic count, which involves quantifying the number of cells in the process of dividing (i.e., undergoing mitosis) at a specific point in time. Currently, mitosis counting is done manually by a pathologist looking at multiple high power fields (HPFs) on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical, or textural attributes of mitoses or features learned with convolutional neural networks (CNN). Although handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely supervised feature generation methods, there is an appeal in attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. We present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color, and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing the performance by leveraging the disconnected feature sets. Evaluation on the public ICPR12 mitosis dataset that has 226 mitoses annotated on 35 HPFs ([Formula: see text] magnification) by several pathologists and 15 testing HPFs yielded an [Formula: see text]-measure of 0.7345. Our approach is accurate, fast, and requires fewer computing resources compared to existent methods, making this feasible for clinical use.

A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection.

This paper presents and evaluates a deep learning architecture for automated basal cell carcinoma cancer detection that integrates (1) image representation learning, (2) image classification and (3) result interpretability. A novel characteristic of this approach is that it extends the deep learning architecture to also include an interpretable layer that highlights the visual patterns that contribute to discriminate between cancerous and normal tissues patterns, working akin to a digital staining which spotlights image regions important for diagnostic decisions. Experimental evaluation was performed on set of 1,417 images from 308 regions of interest of skin histopathology slides, where the presence of absence of basal cell carcinoma needs to be determined. Different image representation strategies, including bag of features (BOF), canonical (discrete cosine transform (DCT) and Haar-based wavelet transform (Haar)) and proposed learned-from-data representations, were evaluated for comparison. Experimental results show that the representation learned from a large histology image data set has the best overall performance (89.4% in F-measure and 91.4% in balanced accuracy), which represents an improvement of around 7% over canonical representations and 3% over the best equivalent BOF representation.

A visual latent semantic approach for automatic analysis and interpretation of anaplastic medulloblastoma virtual slides.

A method for automatic analysis and interpretation of histopathology images is presented. The method uses a representation of the image data set based on bag of features histograms built from visual dictionary of Haar-based patches and a novel visual latent semantic strategy for characterizing the visual content of a set of images. One important contribution of the method is the provision of an interpretability layer, which is able to explain a particular classification by visually mapping the most important visual patterns associated with such classification. The method was evaluated on a challenging problem involving automated discrimination of medulloblastoma tumors based on image derived attributes from whole slide images as anaplastic or non-anaplastic. The data set comprised 10 labeled histopathological patient studies, 5 for anaplastic and 5 for non-anaplastic, where 750 square images cropped randomly from cancerous region from whole slide per study. The experimental results show that the new method is competitive in terms of classification accuracy achieving 0.87 in average.

Visual pattern mining in histology image collections using bag of features.

OBJECTIVE: The paper addresses the problem of finding visual patterns in histology image collections. In particular, it proposes a method for correlating basic visual patterns with high-level concepts combining an appropriate image collection representation with state-of-the-art machine learning techniques. METHODOLOGY: The proposed method starts by representing the visual content of the collection using a bag-of-features strategy. Then, two main visual mining tasks are performed: finding associations between visual-patterns and high-level concepts, and performing automatic image annotation. Associations are found using minimum-redundancy-maximum-relevance feature selection and co-clustering analysis. Annotation is done by applying a support-vector-machine classifier. Additionally, the proposed method includes an interpretation mechanism that associates concept annotations with corresponding image regions. The method was evaluated in two data sets: one comprising histology images from the different four fundamental tissues, and the other composed of histopathology images used for cancer diagnosis. Different visual-word representations and codebook sizes were tested. The performance in both concept association and image annotation tasks was qualitatively and quantitatively evaluated. RESULTS: The results show that the method is able to find highly discriminative visual features and to associate them to high-level concepts. In the annotation task the method showed a competitive performance: an increase of 21% in f-measure with respect to the baseline in the histopathology data set, and an increase of 47% in the histology data set. CONCLUSIONS: The experimental evidence suggests that the bag-of-features representation is a good alternative to represent visual content in histology images. The proposed method exploits this representation to perform visual pattern mining from a wider perspective where the focus is the image collection as a whole, rather than individual images.

Automatic annotation of histopathological images using a latent topic model based on non-negative matrix factorization.

Histopathological images are an important resource for clinical diagnosis and biomedical research. From an image understanding point of view, the automatic annotation of these images is a challenging problem. This paper presents a new method for automatic histopathological image annotation based on three complementary strategies, first, a part-based image representation, called the bag of features, which takes advantage of the natural redundancy of histopathological images for capturing the fundamental patterns of biological structures, second, a latent topic model, based on non-negative matrix factorization, which captures the high-level visual patterns hidden in the image, and, third, a probabilistic annotation model that links visual appearance of morphological and architectural features associated to 10 histopathological image annotations. The method was evaluated using 1,604 annotated images of skin tissues, which included normal and pathological architectural and morphological features, obtaining a recall of 74% and a precision of 50%, which improved a baseline annotation method based on support vector machines in a 64% and 24%, respectively.

Cuantificación de los melanocitos en la piel facial: otra ayuda para evaluar los bordes de resección del melanoma / Quantification of melanocytes in facial skin: another help for evaluation of resection borders of melanoma

Introducción: Los melanocitos epidérmicos están ampliamente separados entre sí, rodeados por un halo; son de citoplasma claro y núcleo picnótico, más pequeño que el de los queratocitos. En la cara es difícil diferenciar entre los cambios por exposición solar y un melanoma in situ, así como establecer si los bordes de resección de un melanoma in situ tienen tumor o si los melanocitos presentes sólo tienen cambios por el sol. Objetivo: Cuantificar el número de melanocitos en adultos normales y en los bordes de resección sin tumor, de carcinomas basocelulares y de melanomas in situ de la piel malar. Materiales y métodos: Se estudiaron veinticinco especímenes de piel tipo I-II de la mejilla de adultos mayores de 40 años, siete de autopsias de hombres, once de los bordes de carcinomas basocelulares y siete de los bordes de resección de melanomas in situ, libres de tumor. Con la coloración de hematoxilina-eosina, tres observadores contaron los melanocitos basales por milímetro lineal en cada espécimen, usando un fotomicroscopio Axiophot Zeiss. Resultados: En un milímetro lineal (3 campos de 40X), el número de melanocitos fue de 18±3 en la piel normal, de 22±7 en los bordes del carcinoma basocelular y de 30±9 en los del melanoma in situ. Conclusiones: El número máximo de melanocitos en un campo de 40X en los tejidos estudiados no debe exceder de 7,5±4 (30 melanocitos) por mm lineal. Un número mayor es una alerta que debe unirse a otros cambios para determinar si hay persistencia de melanoma in situ.