box What is already known about this subject? ► Computer-assisted systems for health image analysis have improved the medical decision-making process for diagnosing and analysing the progression of various diseases. ► Diseases affecting gastric tissue are a worldwide health problem. ► Deep learning applications presented good results in different domains, however its application on gastric tissue analysis is recent, poorly analysed, and standardised. What are the new findings? ► We provide a literature categorisation, based on the method and related tasks, identifying the most widely adopted deep learning architecture and data source used. ► This is the first systematic review dedicated to map gastric tissue deep learning applications covering a broad spectrum, also listing and evaluating open source tools. ► We identified gaps evaluation metrics, image collection availability and, consequently, implications for experimental reproducibility.How might it impact on clinical practice in the foreseeable future?► Deep learning applications can provide greater and more efficient workflow support and extraction of important information from histological images, consequently, replicable studies need to be conducted clearly, and transparently, also providing the data used.AbSTrACT background In recent years, deep learning has gained remarkable attention in medical image analysis due to its capacity to provide results comparable to specialists and, in some cases, surpass them. Despite the emergence of deep learning research on gastric tissues diseases, few intensive reviews are addressing this topic.Method We performed a systematic review related to applications of deep learning in gastric tissue disease analysis by digital histology, endoscopy and radiology images.Conclusions This review highlighted the high potential and shortcomings in deep learning research studies applied to gastric cancer, ulcer, gastritis and non-malignant diseases. Our results demonstrate the effectiveness of gastric tissue analysis by deep learning applications. Moreover, we also identified gaps of evaluation metrics, and image collection availability, therefore, impacting experimental reproducibility.

RESUMOEmpresas no pólo industrial do município de Barcarena-PA utilizam matérias primas, insumos e energia e geram resíduos sólidos, efluentes industriais e esgoto doméstico que são lançados em corpos receptores, alterando as suas características físicas, químicas e microbiológicas. Visando determinar a influência das empresas localizadas no pólo industrial de Barcarena, foi realizado um estudo em um trecho do Rio Pará que sofre influência do lançamento de efluentes industriais das empresas em operação. Para tal, foram selecionados quatro pontos amostrais onde foram realizadas duas campanhas, sendo uma realizada no período menos chuvoso e outra no período chuvoso. Em cada campanha, foram coletadas amostras simultaneamente nos quatro pontos de amostragem durante um período de 12 horas, com intervalos de 90 minutos, iniciando e terminando a coleta no final da vazante. Foram coletadas 36 amostras nos 4 pontos selecionados em cada campanha de amostragem da maré, totalizando 72 amostras nas duas campanhas realizadas. Nas amostras, foram quantificadas variáveis hídricas como: pH, temperatura, condutividade, sólidos totais dissolvidos (STD), cor, sódio, cálcio, potássio, cloreto, alcalinidade e dureza. Os dados foram analisados utilizando o teste estatístico ANOVA de dois fatores com a finalidade de observar se as diferentes variáveis analisadas apresentavam diferenças significativas entre os pontos de amostragem e a sazonalidade, usando nível de significância de 95%. Foi também calculado o Índice de Qualidade de Água (IQA-CETESB). Os testes estatísticos mostraram que a localização dos pontos de amostragem não exerceu influência nos teores médios de pH, porém houve influência significativa para as demais variáveis. Quanto à sazonalidade, houve diferença significativa em praticamente todas as variáveis, com exceção do cloreto e alcalinidade. As amostras de águas apresentaram IQA de qualidade ótima e boa.Palavras-chave: água, ANOVA, efluentes.Characterization of water quality parameters in the port area of Barcarena, PA, Brazil ABSTRACTCompanies in the industrial hub of Barcarena-PA city use raw materials, supplies and energy that generate solid waste, industrial effluents and domestic sewage that are released in

The role of regulatory elements such as small ncRNAs and their mechanisms are poorly understood in infectious diseases. Tuberculosis is one of the oldest infectious diseases of humans and it is still a challenge to prevent and treat. Control of the infection, as well as its diagnosis, are still complex and current treatments used are linked to several side effects. This study aimed to identify possible biomarkers for tuberculosis by applying NGS techniques to obtain global miRNA expression profiles from 22 blood samples of infected patients with tuberculosis (n = 9), their respective healthy physicians (n = 6) and external healthy individuals as controls (n = 7). Samples were run through a pipeline consisting of differential expression, target genes, gene set enrichment and miRNA–gene network analyses. We observed 153 altered miRNAs, among which only three DEmiRNAs (hsa-let-7g-5p, hsa-miR-486-3p and hsa-miR-4732-5p) were found between the investigated patients and their respective physicians. These DEmiRNAs are suggested to play an important role in granuloma regulation and their immune physiopathology. Our results indicate that miRNAs may be involved in immune modulation by regulating gene expression in cells of the immune system. Our findings encourage the application of miRNAs as potential biomarkers for tuberculosis.

O presente estudo objetivou a classificação de tipologias florestais por meio de redes neurais artificiais utilizando dados provenientes de um inventário florestal, fornecido pelo Instituto de Desenvolvimento Florestal e da Biodiversidade do Estado do Pará (IDEFLOR-BIO), e das bandas 3, 4 e 5 do TM do satélite Landsat 5. As informações provenientes das imagens de satélite foram extraídas por meio do aplicativo QGIS 2.8.1 Wien e utilizadas no banco de dados para o treinamento das redes neurais pertencentes às ferramentas do software MATLAB® R2011b. Foram treinadas redes neurais como classificadores de dois tipos florestais: Floresta Ombrófila Densa de Terras baixas Dossel emergente (Dbe) e Floresta Ombrófila Densa Terras baixas Dossel emergente mais Aberta com palmeiras (Dbe + Abp) no conjunto de glebas estaduais Mamuru Arapiuns, Pará, e avaliadas usando os indicadores matriz de confusão, cálculo de acurácia global, coeficiente Kappa e o gráfico de características do receptor operacional (ROC). O melhor resultado de classificação foi obtido por meio da rede neural probabilística de função de base radial (RBF) “newpnn”, com uma acurácia global de 88%, e coeficiente Kappa de 76%, sendo avaliado como um classificador muito bom, evidenciando a aplicação dessa metodologia na análise de áreas com potencial para prestar serviços ecossistêmicos e, principalmente, na prestação de serviços ambientais em áreas antrópicas que adotam sistema de produção agropecuária com baixa emissão de carbono na Amazônia.

The state of Pará has experienced a high occurrence of forest fires, which were strongly influenced by the El Niño phenomenon in 2015-2016. This study aims to analyze the conditions of heat sources in Pará, using the 2016 monthly bulletins provided by the Environment and Sustainability Secretariat. This data was analyzed through descriptive statistics. The IDW interpolation method was used to construct the density map, displaying the primary areas of concern. The results showed that the greatest detections were during the Amazonian summer, occurring during the second half of the year. Specifically, the municipalities of the Southwestern and Southeastern Para meso-regions were mainly the ones affected. Fire is used as a primary economic tool. The Southwest was the one region that presented the highest densities of hotspots. Although the results do not indicate the actual configuration of the events, because of the technical limitations of remote sensing, the information obtained in this study communicates ideas concerning prevention and action in the most affected areas. In loco studies are needed to determine precisely the causes of these occurrences.