The segmentation and characterization of the lung lobes are important tasks for Computer Aided Diagnosis (CAD) systems related to pulmonary disease. The detection of the fissures that divide the lung lobes is non-trivial when using classical methods that rely on anatomical information like the localization of the airways and vessels. This work presents a fully automatic and supervised approach to the problem of the segmentation of the five pulmonary lobes from a chest Computer Tomography (CT) scan using a Fully Regularized V-Net (FRV-Net), a 3D Fully Convolutional Neural Network trained end-toend. Our network was trained and tested in a custom dataset that we make publicly available. It can correctly separate the lobes even in cases when the fissure is not well delineated, achieving 0.93 in per-lobe Dice Coefficient and 0.85 in the inter-lobar Dice Coefficient in the test set. Both quantitative and qualitative results show that the proposed method can learn to produce correct lobe segmentations even when trained on a reduced dataset.
Wide inequalities in TB notification rates were observed, and some areas continued to exhibit high TB notification rates. We found significant associations between TB and some socio-economic factors of the EDI.
Breast cancer is one of the leading causes of female death worldwide. The histological analysis of breast tissue allows for the differentiation of the tissue suspected to be abnormal into four classes: normal tissue, benign tumor, in situ carcinoma and invasive carcinoma. Automatic diagnostic systems can help in that task. In this sense, this work propose a deep neural network approach using transfer learning to classify breast cancer histology images. First, the added top layers are trained and a second fine-tunning is done on some feature extraction layers that are frozen previously. The used network is an Inception Resnet V2. In order to overcome the lack of data, data augmentation is performed too. This work is a suggested solution for the ICIAR 2018 BACH-Challenge and the accuracy is 0.76 in the blind test set.
The 250 × 20-70 km Iberian Pyrite Belt (IPB) is a Variscan metallogenic province in SW Portugal and Spain hosting the largest concentration of massive sulphide deposits worldwide. The lowermost stratigraphic unit is the early Givetian to late Famennian-Strunian (base unknown) PhylliteQuartzite Group (PQG), with shales, quartz-sandstones, quartzwacke siltstones, minor conglomerate and limestones at the top. The PQG is overlain by the Volcanic Sedimentary Complex (VSC), of late Famennian to mid-late Visean age, with a lower part of mafic volcanic rocks, rhyolites, dacites and dark shales, hosting VHMS deposits on top (many times capped by a jasper/chert layer), and an upper part, with dark, purple and other shales and volcanogenic/volcaniclastic rocks, carrying Mn oxide deposits. The VSC is covered by the thousands of meters thick Baixo Alentejo Flysch Group of late Visean to Moscovian age. The VSC
Purpose
The Portuguese tax authority implemented a lottery to encourage citizens to request invoices as a strategy to fight value-added tax (VAT) evasion. As the law does not require citizens to request sales invoices with the consumers’ tax number, doing so is a form of voluntary cooperation in tracking down tax evaders. The purpose of this paper is to understand why ordinary citizens decide to join forces with tax authorities in the fight against VAT evasion by requesting invoices with their tax identification number.
Design/methodology/approach
An empirical study was conducted to explore the underlying motivation for Portuguese consumers to request sales invoices with their personal tax identification. The study combines quantitative and qualitative data.
Findings
The results from this study show that rewarding citizens is clearly a factor to be considered in any policy to maximize citizens’ cooperation in tracking down tax evaders. They indicate that fiscal benefits have a stronger effect on the request of invoices than the lottery and that it is necessary to promote good governance and justice.
Practical implications
Findings should be used to inform a cost-effective public policy that takes into account citizens’ concerns and combine deterrent measures and rewards in the form of tax benefits, rather than tax lotteries.
Originality/value
This paper provides new insights into VAT lotteries, which seem to be increasingly favored by policy makers but are an area under-researched. By recommending a course of action to maximize citizens’ cooperation in tracking down tax evaders, the paper provides useful practical implications and is a contribution for the study of VAT evasion policies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.