Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images.

We present an Unsupervised Domain Adaptation strategy to compensate for domain shifts on Electron Microscopy volumes. Our method aggregates visual correspondences-motifs that are visually similar across different acquisitions-to infer changes on the parameters of pretrained models, and enable them to operate on new data. In particular, we examine the annotations of an existing acquisition to determine pivot locations that characterize the reference segmentation, and use a patch matching algorithm to find their candidate visual correspondences in a new volume. We aggregate all the candidate correspondences by a voting scheme and we use them to construct a consensus heatmap: a map of how frequently locations on the new volume are matched to relevant locations from the original acquisition. This information allows us to perform model adaptations in two different ways: either by a) optimizing model parameters under a Multiple Instance Learning formulation, so that predictions between reference locations and their sets of correspondences agree, or by b) using high-scoring regions of the heatmap as soft labels to be incorporated in other domain adaptation pipelines, including deep learning ones. We show that these unsupervised techniques allow us to obtain high-quality segmentations on unannotated volumes, qualitatively consistent with results obtained under full supervision, for both mitochondria and synapses, with no need for new annotation effort.

The effects of aging on neuropil structure in mouse somatosensory cortex-A 3D electron microscopy analysis of layer 1.

This study has used dense reconstructions from serial EM images to compare the neuropil ultrastructure and connectivity of aged and adult mice. The analysis used models of axons, dendrites, and their synaptic connections, reconstructed from volumes of neuropil imaged in layer 1 of the somatosensory cortex. This shows the changes to neuropil structure that accompany a general loss of synapses in a well-defined brain region. The loss of excitatory synapses was balanced by an increase in their size such that the total amount of synaptic surface, per unit length of axon, and per unit volume of neuropil, stayed the same. There was also a greater reduction of inhibitory synapses than excitatory, particularly those found on dendritic spines, resulting in an increase in the excitatory/inhibitory balance. The close correlations, that exist in young and adult neurons, between spine volume, bouton volume, synaptic size, and docked vesicle numbers are all preserved during aging. These comparisons display features that indicate a reduced plasticity of cortical circuits, with fewer, more transient, connections, but nevertheless an enhancement of the remaining connectivity that compensates for a generalized synapse loss.

Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences.

We propose a novel approach to automatically tracking elliptical cell populations in time-lapse image sequences. Given an initial segmentation, we account for partial occlusions and overlaps by generating an over-complete set of competing detection hypotheses. To this end, we fit ellipses to portions of the initial regions and build a hierarchy of ellipses, which are then treated as cell candidates. We then select temporally consistent ones by solving to optimality an integer program with only one type of flow variables. This eliminates the need for heuristics to handle missed detections due to partial occlusions and complex morphology. We demonstrate the effectiveness of our approach on a range of challenging sequences consisting of clumped cells and show that it outperforms state-of-the-art techniques.

Linking genetic and environmental factors in amphibian disease risk.

A central question in evolutionary biology is how interactions between organisms and the environment shape genetic differentiation. The pathogen Batrachochytrium dendrobatidis (Bd) has caused variable population declines in the lowland leopard frog (Lithobates yavapaiensis); thus, disease has potentially shaped, or been shaped by, host genetic diversity. Environmental factors can also influence both amphibian immunity and Bd virulence, confounding our ability to assess the genetic effects on disease dynamics. Here, we used genetics, pathogen dynamics, and environmental data to characterize L. yavapaiensis populations, estimate migration, and determine relative contributions of genetic and environmental factors in predicting Bd dynamics. We found that the two uninfected populations belonged to a single genetic deme, whereas each infected population was genetically unique. We detected an outlier locus that deviated from neutral expectations and was significantly correlated with mortality within populations. Across populations, only environmental variables predicted infection intensity, whereas environment and genetics predicted infection prevalence, and genetic diversity alone predicted mortality. At one locality with geothermally elevated water temperatures, migration estimates revealed source-sink dynamics that have likely prevented local adaptation. We conclude that integrating genetic and environmental variation among populations provides a better understanding of Bd spatial epidemiology, generating more effective conservation management strategies for mitigating amphibian declines.

Domain adaptation for microscopy imaging.

Electron and light microscopy imaging can now deliver high-quality image stacks of neural structures. However, the amount of human annotation effort required to analyze them remains a major bottleneck. While machine learning algorithms can be used to help automate this process, they require training data, which is time-consuming to obtain manually, especially in image stacks. Furthermore, due to changing experimental conditions, successive stacks often exhibit differences that are severe enough to make it difficult to use a classifier trained for a specific one on another. This means that this tedious annotation process has to be repeated for each new stack. In this paper, we present a domain adaptation algorithm that addresses this issue by effectively leveraging labeled examples across different acquisitions and significantly reducing the annotation requirements. Our approach can handle complex, nonlinear image feature transformations and scales to large microscopy datasets that often involve high-dimensional feature spaces and large 3D data volumes. We evaluate our approach on four challenging electron and light microscopy applications that exhibit very different image modalities and where annotation is very costly. Across all applications we achieve a significant improvement over the state-of-the-art machine learning methods and demonstrate our ability to greatly reduce human annotation effort.

Learning structured models for segmentation of 2-D and 3-D imagery.

Efficient and accurate segmentation of cellular structures in microscopic data is an essential task in medical imaging. Many state-of-the-art approaches to image segmentation use structured models whose parameters must be carefully chosen for optimal performance. A popular choice is to learn them using a large-margin framework and more specifically structured support vector machines (SSVM). Although SSVMs are appealing, they suffer from certain limitations. First, they are restricted in practice to linear kernels because the more powerful nonlinear kernels cause the learning to become prohibitively expensive. Second, they require iteratively finding the most violated constraints, which is often intractable for the loopy graphical models used in image segmentation. This requires approximation that can lead to reduced quality of learning. In this paper, we propose three novel techniques to overcome these limitations. We first introduce a method to "kernelize" the features so that a linear SSVM framework can leverage the power of nonlinear kernels without incurring much additional computational cost. Moreover, we employ a working set of constraints to increase the reliability of approximate subgradient methods and introduce a new way to select a suitable step size at each iteration. We demonstrate the strength of our approach on both 2-D and 3-D electron microscopic (EM) image data and show consistent performance improvement over state-of-the-art approaches.

Fast part-based classification for instrument detection in minimally invasive surgery.

Automatic visual detection of instruments in minimally invasive surgery (MIS) can significantly augment the procedure experience for operating clinicians. In this paper, we present a novel technique for detecting surgical instruments by constructing a robust and reliable instrument-part detector. While such detectors are typically slow to use, we introduce a novel early stopping scheme for multiclass ensemble classifiers which acts as a cascade and significantly reduces the computational requirements at test time, ultimately allowing it to run at framerate. We evaluate the effectiveness of our approach on instrument detection in retinal microsurgery and laparoscopic image sequences and demonstrate significant improvements in both accuracy and speed.

Exploiting enclosing membranes and contextual cues for mitochondria segmentation.

In this paper, we improve upon earlier approaches to segmenting mitochondria in Electron Microscopy images by explicitly modeling the double membrane that encloses mitochondria, as well as using features that capture context over an extended neighborhood. We demonstrate that this results in both improved classification accuracy and reduced computational requirements for training.

Registro prospectivo de estrategias diagnósticas implementadas para tromboembolia venosa en servicios de medicina intensiva de Santa Fe / Prospective Registry of Diagnostic Strategies Applied on Venous Thromboembolism in Intensive Care Units of Santa Fe

Introducción La tromboembolia venosa es una enfermedad frecuente con una morbimortalidad elevada, que puede reducirse en forma drástica cuando la condición se reconoce y trata precozmente. Su diagnóstico tropieza con dos dificultades: la baja sospecha clínica y la complejidad de los recursos técnicos requeridos no siempre disponibles, lo que dificulta la aplicación de los algoritmos propuestos en las guías. Objetivos Evaluar las estrategias diagnósticas en los servicios de cuidados intensivos de la ciudad de Santa Fe ante la sospecha de tromboembolia venosa, identificar si se utiliza algún algoritmo diagnóstico y el grado de incertidumbre diagnóstica final. Material y métodos Se convocó a todos los servicios de cuidados intensivos para adultos de la ciudad de Santa Fe para la elaboración de un registro prospectivo, multicéntrico y observacional con el reclutamiento de los pacientes internados con sospecha de tromboembolia venosa [(trombosis venosa profunda (TVP) y/o tromboembolia pulmonar (TEP)]. Resultados En un período de 3 meses y medio se internaron 3.042 pacientes en los 19 servicios de cuidados intensivos de la ciudad. Se sospechó tromboembolia venosa en 83 pacientes (50 TEP, 10 TVP y 23 TEP + TVP). El diagnóstico se confirmó en 25 (30,1%), se descartó en 33 (39,8%) y permaneció incierto en 25 (30,1%). La incertidumbre diagnóstica final fue del 25,7% en los servicios privados y del 66,6% en los públicos. La tasa de sospecha fue del 2,7% (rango 0,9% a 8,8%). No hubo empleo sistemático de guías clínicas ni de consensos conocidos. Conclusiones Este registro mostró un índice de sospecha global bajo para tromboembolia venosa, no se utilizaron los algoritmos diagnósticos propuestos en guías y consensos y el diagnóstico per­maneció incierto en el 30,1%.

Introduction Venous thromboembolism is a common disease with high morbidity and mortality which can be reduced drastically with early diagnosis and treatment. The diagnosis of venous thromboembolism faces two difficulties: the low clinical suspicion and the complexity of the technical resources required which are not always available, making it difficult to apply the algorithms recommended by the guidelines. Objectives The evaluate the diagnostic strategies used by the intensive care units in the city of Santa Fe when venous thromboembolism suspected, and to identify if any diagnostic algorithm is applied and the degree of final uncertain diagnosis. Methods A prospective multicenter and observational registry of patients hospitalized with suspicion of venous thromboembolism [(deep venous thrombosis (DVT) and/or pulmonary embolism (PE)] was elaborated by all the adult intensive care units. Results Over a three and a half-month period, 3042 patients were hospitalized in the 19 intensive care units of the city. Venous thromboembolism was suspected in 83 patients (50 PE, 10 DVT and 23 PE + DVT). The diagnosis was confirmed in 25 (30.1%), was ruled out in 33 (39.8%) and remained uncertain in 25 (30.1%). The final uncertain diagnosis was 25.7% in private centers and 66.6% in public hospitals. The index of suspicion was 2.7% (range 0.9% to 8.8%). The algorithms recommended by guidelines were not systematically used. Conclusions This registry showed a low global index of suspicion for venous thromboembolism, the algorithms recommended by guidelines were not used and the final uncertain diagnosis was 30.1%.

Análisis retrospectivo de una población de pacientes con síndrome de Brugada y cardiodesfibrilador automático implantable / Retrospective Analysis of Patients with Brugada Syndrome and Implantable Cardioverter Defibrillator

Introducción El síndrome de Brugada es una anomalía eléctrica hereditaria con riesgo incrementado de muerte súbita. El cardiodesfibrilador automático implantable es el único tratamiento efectivo para la prevención de la muerte súbita, mientras que la conducta terapéutica en los pacientes asintomáticos continúa siendo controversial. Objetivos Evaluar la incidencia y las causas de choques apropiados e inapropiados y las complicaciones relacionadas con el dispositivo. Identificar la relación de variables clínicas y del estudio electrofisiológico con la ocurrencia de choques apropiados. Material y métodos Registro unicéntrico, retrospectivo de pacientes con síndrome de Brugada, con patrón electrocardiográfico tipo I espontáneo o inducido con infusión de ajmalina, a quienes se les colocó un cardiodesfibrilador automático implantable. Resultados Se incluyeron 21 pacientes, 18 hombres, con una mediana de edad de 40 años. El dispositivo fue indicado por síntomas -respiración agónica nocturna, síncope y paro cardíaco resucitado- o por un estudio electrofisiológico positivo en pacientes asintomáticos. En un seguimiento de 88 meses no hubo muertes; la tasa anual de choques apropiados fue del 1,9%, inferior a la de choques inapropiados (7,5%). Diez pacientes tuvieron complicaciones, que incluyeron infección del dispositivo y trastornos psiquiátricos. La única variable relacionada significativamente con la presencia de choques apropiados fue el antecedente de fibrilación y aleteo auricular. Conclusiones Se observó una tasa anual baja de choques apropiados. Las dificultades en la estratificación del riesgo, la alta incidencia de choques inapropiados y la elevada frecuencia de complicaciones hacen recomendable una selección cuidadosa para el implante de estos dispositivos hasta encontrar predictores más confiables de riesgo arrítmico.

Introduction The Brugada syndrome is an inherited, electrical anomaly, with increased risk of sudden cardiac death. Automatic cardioverter defibrillators are the only effective treatment to prevent sudden cardiac death, while therapy management in asymptomatic patients is still controversial. Objectives The aims of the study were to evaluate the incidence and causes of appropriate and inappropriate shocks and the complications related to the device, and to identify the relation of clinical and electrophysiological study variables with the incidence of appropriate shocks. Methods This was a single-center, retrospective registry of patients with Brugada syndrome, with type-1 electrocardiographic pattern, either spontaneous or induced by ajmaline infusion, who were recipients of automatic implantable cardioverter defibrillator. Results Twenty-one patients were included in the study; 18 were males, and average age was 40 years. The device was indicated due to the following symptoms: nocturnal agonal respiration, syncope and aborted cardiac arrest, or positive electrophysiology study in asymptomatic patients. There were no deaths during follow-up of 88 months, and the yearly rate of appropriate shocks was 1.9%, below that of inappropriate shocks (7.5%). Ten patients presented complications including device infection and psychiatric disorders. The only variable significantly related with the presence of appropriate shocks was history of fibrillation and atrial flutter. Conclusions A low yearly rate of appropriate shocks was observed. The difficulties in risk stratification, the high incidence of inappropriate shocks and the high frequency of complications indicate need of careful patient selection for the implantation of these devices until more reliable predictors of arrhythmic risk are found.

Melting curve analysis for the screening of hepatitis B virus genotypes A, D and F in patients from a general hospital in southern Brazil.

CONTEXT: Hepatitis B virus (HBV) can cause fulminant hepatitis, cirrhosis and hepatocellular carcinoma, and is one of the most common causes of acute and chronic liver failure. The genetic variants of HBV can be decisive for the evolution of these diseases as well as for the election of therapy. OBJECTIVES: The aim of this study was to evaluate and standardize an in house methodology based on the analysis of the melting curve polymerase chain reaction (PCR) of real-time (qPCR) to screen for genotypes A, D and F of HBV in patients from a hospital in Rio Grande do Sul, Brazil. METHODS: We evaluated 104 patients presumably with HBV chronic infection. Viral DNA was extracted from plasma and viral genotypes and different mutations were determined using PCR-based protocols. RESULTS: A PCR-based methodology was standardized for the analysis of genotypes A, D and F of HBV. The technique was based in a nested PCR with the final step consisting of a multiplex real-time PCR, using the melting curve as a tool for the differentiation of fragments. A higher frequency of genotype D (44.4%), followed by genotype A (22.2%) and genotype F (3.7%) was observed. CONCLUSION: The standardized assay, a nested PCR-multiplex qPCR using specific primers, provides a rapid and accurate method for the differentiation of HBV genotypes that are more frequent in Southern Brazil - A, D and F. This method can be applied in the clinical practice.

Melting curve aaalysis for the screening of heptitis b virus genotypes a, d annd f in patients from a general hospital in southern Brazil / Analise da curva de melting para o screening dos genotipos A, D e F do virus da hepatite B em pacientes de um hospital geral do sul do Brasil.

Context Hepatitis B virus (HBV) can cause fulminant hepatitis, cirrhosis and hepatocellular carcinoma, and is one of the most common causes of acute and chronic liver failure. The genetic variants of HBV can be decisive for the evolution of these diseases as well as for the election of therapy. Objectives The aim of this study was to evaluate and standardize an in house methodology based on the analysis of the melting curve polymerase chain reaction (PCR) of real-time (qPCR) to screen for genotypes A, D and F of HBV in patients from a hospital in Rio Grande do Sul, Brazil. Methods We evaluated 104 patients presumably with HBV chronic infection. Viral DNA was extracted from plasma and viral genotypes and different mutations were determined using PCR-based protocols. Results A PCR-based methodology was standardized for the analysis of genotypes A, D and F of HBV. The technique was based in a nested PCR with the final step consisting of a multiplex real-time PCR, using the melting curve as a tool for the differentiation of fragments. A higher frequency of genotype D (44.4%), followed by genotype A (22.2%) and genotype F (3.7%) was observed. Conclusion The standardized assay, a nested PCR-multiplex qPCR using specific primers, provides a rapid and accurate method for the differentiation of HBV genotypes that are more frequent in Southern Brazil – A, D and F. This method can be applied in the clinical practice. .

Contexto O vírus da hepatite B pode causar hepatite fulminante, cirrose e carcinoma hepatocelular, sendo uma das causas mais frequentes de doença aguda e crônica do fígado. As variantes genéticas do VHB podem ser determinantes para a evolução da doenças assim como para a eleição da terapêutica. Objetivos O objetivo deste estudo foi padronizar e avaliar uma metodologia “in house”, através da utilização da curva de melting de reação em cadeia da polimerase (PCR) em tempo real (qPCR), como rastreamento para análise dos genótipos A, D e F do vírus da hepatite B em pacientes do Rio Grande do Sul. Métodos Foram avaliados 104 pacientes supostamente com infecção crônica pelo VHB. O DNA foi extraído com kit comercial, os genótipos e as mutações foram determinados utilizando diferentes protolocos baseados em PCR. Resultados Foi padronizada uma metodologia baseada em PCR para a análise dos genótipos A, D e F do VHB. A técnica consistiu de uma PCR Nested incluindo uma etapa final de PCR em tempo real Multiplex, utilizando a curva de melting como ferramenta para a definição dos fragmentos. Foi observada uma maior frequência do genótipo D (44,4%), seguido do genótipo A (22,2%) e do genótipo F (3,7%) na amostra analisada. Conclusão O ensaio padronizado fornece um método rápido e preciso para diferenciar genótipos do VHB mais frequentes no sul do Brasil – A, D e F – usando um PCR Nested Multiplex com primers específicos, o qual apresenta potencial aplicação na prática clínica. .

Learning context cues for synapse segmentation.

We present a new approach for the automated segmentation of synapses in image stacks acquired by electron microscopy (EM) that relies on image features specifically designed to take spatial context into account. These features are used to train a classifier that can effectively learn cues such as the presence of a nearby post-synaptic region. As a result, our algorithm successfully distinguishes synapses from the numerous other organelles that appear within an EM volume, including those whose local textural properties are relatively similar. Furthermore, as a by-product of the segmentation, our method flawlessly determines synaptic orientation, a crucial element in the interpretation of brain circuits. We evaluate our approach on three different datasets, compare it against the state-of-the-art in synapse segmentation and demonstrate our ability to reliably collect shape, density, and orientation statistics over hundreds of synapses.

[Possible prognostic value of atrial fibrillation and atrial flutter in Brugada syndrome]. / Posible valor pronóstico de la fibrilación y el flutter auricular en el síndrome de Brugada.

OBJECTIVE: To analyze the specific risk for the variables: type 1 spontaneous pattern, type 1 induced pattern, type 1 pattern with spontaneous variability, syncope, family history of sudden death, atrial fibrillation and atrial flutter with the subsequent development of malignant arrhythmic events. METHODS: Forty-three Brugada patients (90% males; mean age 40.4 years), with a type 1 spontaneous pattern (74.4%) or induced by ajmaline (25.6%) were retrospectively analyzed. Of these, 58.1% presented spontaneous variability, 18.6% had family history of sudden death, 39.5% were symptomatic, and 18.6% presented atrial fibrillation or atrial flutter. The antecedents of resuscitated cardiac arrest, sudden death or appropriate shock from implantable automatic defibrillator were considered malignant arrhythmic events. During a mean follow up of 51 months, no deaths were recorded, 6.9% of the patients presented a malignant arrhythmic event, and all of them were appropriate shocks. The annual rate of events in patients with syncope was 1.7%, with a spontaneous type 1 pattern was 2.79%, and spontaneous variability was 2.87%. No malignant arrhythmic event was observed in asymptomatic patients or in those with a persistent pattern or induced type 1 pattern. The annual rate of events with positive or negative history of family sudden death was 2.94 and 1.7%, respectively. In the presence of atrial fibrillation, atrial flutter and atrial fibrillation/atrial flutter were 7.3, 15.69 and 10%, respectively. In the absence of atrial fibrillation/atrial flutter no malignant arrhythmic events were observed. CONCLUSION: Of the variables analyzed, the one that was most related to a malignant arrhythmic event was the presence of atrial fibrillation (P=.046) and atrial flutter (P=.03).

Posible valor pronóstico de la fibrilación y el flutter auricular en el síndrome de Brugada / Possible prognostic value of atrial fibrillation and atrial flutter in Brugada syndrome

Objetivo: Analizar el riesgo específico para las variables: patrón tipo 1 espontáneo, patrón tipo 1 inducido, patrón tipo 1 con variabilidad espontánea, síncope, antecedente de muerte súbita familiar, fibrilación auricular y flutter auricular, con el desarrollo subsecuente de eventos arrítmicos malignos. Métodos: Se analizaron retrospectivamente 43 pacientes con síndrome de Brugada (90% hombres; edad media 40.4 años), con patrón tipo 1 espontáneo (74.4%) o inducido por ajmalina (25.6%). El 58.1% presentó variabilidad espontánea. El 18.6% tenía antecedente de muerte súbita familiar. El 39.5% era sintomático. El 18.6% presentó fibrilación auricular o flutter auricular. El antecedente de un paro cardiaco resucitado, muerte súbita o choque apropiado del desfibrilador automático implantable se consideró evento arrítmico maligno. Durante un seguimiento promedio de 51 meses no se registraron muertes, el 6.9% de los pacientes presentó un evento arrítmico maligno, y en su totalidad fueron choques apropiados. La tasa anual de eventos arrítmicos malignos en los pacientes con síncope fue del 1.7%, con un patrón tipo 1 espontáneo, del 2.79%, y con variabilidad espontánea, del 2.87%. No se observaron eventos arrítmicos malignos en los asintomáticos y en aquellos con un patrón persistente o tipo 1 inducido. La tasa anual de eventos con antecedente positivo o negativo de muerte súbita familiar fue del 2.94 y 1.7%, respectivamente. En presencia de fibrilación auricular, flutter auricular y fibrilación auricular/flutter auricular fue del 7.3, 15.69 y 10%, respectivamente. En ausencia de fibrilación/flutter no se observaron eventos arrítmicos malignos. Conclusión: De las variables analizadas, las que tuvieron mayor relación con la presencia de un evento arrítmico maligno fueron la presencia de fibrilación auricular (p = 0,046) y de flutter auricular (p = 0,03).

Objective: To analyze the specific risk for the variables: type 1 spontaneous pattern, type 1 induced pattern, type 1 pattern with spontaneous variability, syncope, family history of sudden death, atrial fibrillation and atrial flutter with the subsequent development of malignant arrhythmic events. Methods: Forty-three Brugada patients (90% males; mean age 40.4 years), with a type 1 spontaneous pattern (74.4%) or induced by ajmaline (25.6%) were retrospectively analyzed. Of these, 58.1% presented spontaneous variability, 18.6% had family history of sudden death, 39.5% were symptomatic, and 18.6% presented atrial fibrillation or atrial flutter. The antecedents of resuscitated cardiac arrest, sudden death or appropriate shock from implantable automatic defibrillator were considered malignant arrhythmic events. During a mean follow up of 51 months, no deaths were recorded, 6.9% of the patients presented a malignant arrhythmic event, and all of them were appropriate shocks. The annual rate of events in patients with syncope was 1.7%, with a spontaneous type 1 pattern was 2.79%, and spontaneous variability was 2.87%. No malignant arrhythmic event was observed in asymptomatic patients or in those with a persistent pattern or induced type 1 pattern. The annual rate of events with positive or negative history of family sudden death was 2.94 and 1.7%, respectively. In the presence of atrial fibrillation, atrial flutter and atrial fibrillation/atrial flutter were 7.3, 15.69 and 10%, respectively. In the absence of atrial fibrillation/atrial flutter no malignant arrhythmic events were observed. Conclusion: Of the variables analyzed, the one that was most related to a malignant arrhythmic event was the presence of atrial fibrillation (P= .046) and atrial flutter (P= .03).

Supervised feature learning for curvilinear structure segmentation.

We present a novel, fully-discriminative method for curvilinear structure segmentation that simultaneously learns a classifier and the features it relies on. Our approach requires almost no parameter tuning and, in the case of 2D images, removes the requirement for hand-designed features, thus freeing the practitioner from the time-consuming tasks of parameter and feature selection. Our approach relies on the Gradient Boosting framework to learn discriminative convolutional filters in closed form at each stage, and can operate on raw image pixels as well as additional data sources, such as the output of other methods like the Optimally Oriented Flux. We will show that it outperforms state-of-the-art curvilinear segmentation methods on both 2D images and 3D image stacks.

Hipertensión pulmonar asociada a neurofibromatosis / Pulmonary hypertension associated to neurofibromatosis / Hipertensão pulmonar associada à neurofibromatose

La hipertensión pulmonar secundaria a enfermedades sistémicas corresponde a una asociación incluida en las últimas guías de diagnóstico y tratamiento de la hipertensión pulmonar de la Sociedad Europea de Cardiología; pero dada su heterogeneidad y rareza, no existe un sustento fisiopatológico. Presentamos el caso de una paciente con hipertensión pulmonar asociada a neurofibromatosis sin otra etiología demostrada.

Pulmonary hypertension secondary to systemic disease belongs to a partnership including in the latest guidelines for diagnosis and treatment of pulmonary hypertension of the European Society of Cardiology, but given the heterogeneity and rarity, there is nopathophysiological support. We report a patient with pulmonary hypertension associated with neurofibromatosis without other etiology demonstrated.

A hipertensão pulmonar secundária a doenças sistêmicas foi incluindo nas diretrizes do diagnóstico e tratamento da hipertensão pulmonar da Sociedade Européia de Cardiologia, mas a fisiopatologia não é clara. Apresentamos um relato de caso do paciente com hipertensão pulmonar associada à neurofibromatose sem etiologia comprovada.

Learning context cues for synapse segmentation in EM volumes.

We present a new approach for the automated segmentation of excitatory synapses in image stacks acquired by electron microscopy. We rely on a large set of image features specifically designed to take spatial context into account and train a classifier that can effectively utilize cues such as the presence of a nearby post-synaptic region. As a result, our algorithm successfully distinguishes synapses from the numerous other organelles that appear within an EM volume, including those whose local textural properties are relatively similar. This enables us to achieve very high detection rates with very few false positives.

Genotyping of hepatitis B virus in a cohort of patients evaluated in a hospital of Porto Alegre, South of Brazil.

CONTEXT: In recent years the hepatitis B virus (HBV) genotyping has been considered a relevant factor in the natural history of the disease. OBJECTIVE: To determine hepatitis B virus genotypes and its epidemiological and clinical implications, in a cohort of patients in a hospital in Porto Alegre, South of Brazil. METHODS: Sixty seven patients with HBV chronic infection markers who were being treated at ''Complexo Hospitalar Santa Casa'', in Porto Alegre, RS, Brazil, were evaluated. Demographic and epidemiological data were collected from these group of patients by following a standard protocol and ALT and HBeAg were determined. The genotypes and subtypes were determined by in-house PCR and, finally, the samples were sequenced. The level of significance used was 5%. RESULTS: The qualitative analysis for HBV-DNA by PCR was positive in 79.1% of the samples (53/67). The genotype was determined in all positive VHB-DNA samples and the genotypes A (34%), D (60.4%) and F (5.4%) as well as the subtypes adw, ayw and adw4 were found. No significant correlation was found between the hepatitis B virus genotypes and demographic variables considered as risk factors for hepatitis B virus infection. There was also no correlation between the genotypes and the serological and laboratory variables related to liver disease. CONCLUSION: We concluded that the most prevalent genotype found was D. However, further studies are needed to allow us to evaluate the implications of genetic variability in the clinical evolution of HBV carriers.

Genotyping of hepatitis B virus in a cohort of patients evaluated in a hospital of Porto Alegre, south of Brazil

CONTEXT: In recent years the hepatitis B virus (HBV) genotyping has been considered a relevant factor in the natural history of the disease. OBJECTIVE: To determine hepatitis B virus genotypes and its epidemiological and clinical implications, in a cohort of patients in a hospital in Porto Alegre, South of Brazil. Methods - Sixty seven patients with HBV chronic infection markers who were being treated at ''Complexo Hospitalar Santa Casa'', in Porto Alegre, RS, Brazil, were evaluated. Demographic and epidemiological data were collected from these group of patients by following a standard protocol and ALT and HBeAg were determined. The genotypes and subtypes were determined by in-house PCR and, finally, the samples were sequenced. The level of significance used was 5 percent. RESULTS: The qualitative analysis for HBV-DNA by PCR was positive in 79.1 percent of the samples (53/67). The genotype was determined in all positive VHB-DNA samples and the genotypes A (34 percent), D (60.4 percent) and F (5.4 percent) as well as the subtypes adw, ayw and adw4 were found. No significant correlation was found between the hepatitis B virus genotypes and demographic variables considered as risk factors for hepatitis B virus infection. There was also no correlation between the genotypes and the serological and laboratory variables related to liver disease. CONCLUSION: We concluded that the most prevalent genotype found was D. However, further studies are needed to allow us to evaluate the implications of genetic variability in the clinical evolution of HBV carriers.

CONTEXTO: Nos últimos anos a genotipagem do vírus da hepatite B (VHB) tem sido considerado fator relevante para a história natural da doença. OBJETIVOS: Determinar os genótipos do VHB e suas implicações clínicas e epidemiológicas, em uma coorte de pacientes em um hospital de Porto Alegre, RS, sul do Brasil. MÉTODOS: Foram avaliados 67 pacientes com marcadores de infecção crônica pelo VHB que estavam sendo tratados no Complexo Hospitalar Santa Casa de Porto Alegre, RS. Foi aplicado um protocolo com dados demográficos e epidemiológicos dos pacientes, e AgHBe e ALT foram determinadas. Os genótipos e subtipos foram determinados por PCR in-house e, finalmente, as amostras foram sequenciadas. O nível de significância utilizado foi de 5 por cento. RESULTADOS: A análise qualitativa de VHB-DNA por PCR foi positiva em 79,1 por cento das amostras (53/67). O genótipo foi determinado em todas as amostras de VHB-DNA positivo. A análise demonstrou a presença dos genótipos A (34 por cento), D (60,4 por cento) e F (5,4 por cento). Foram encontrados os seguintes subtipos: adW, ayw e adw4. Nenhuma correlação significativa foi encontrada entre os genótipos do VHB e as variáveis demográficas estudadas como fator de risco para infecção pelo VHB, e com os exames sorológicos e laboratoriais de doença hepática. CONCLUSÃO: O genótipo mais prevalente encontrado foi o D. No entanto, mais estudos são necessários para que se possa avaliar as implicações da variabilidade genética na evolução clínica de portadores do VHB.