Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and localization of chest abnormalities. In this work, we describe a dataset of more than 100,000 chest X-ray scans that were retrospectively collected from two major hospitals in Vietnam. Out of this raw data, we release 18,000 images that were manually annotated by a total of 17 experienced radiologists with 22 local labels of rectangles surrounding abnormalities and 6 global labels of suspected diseases. The released dataset is divided into a training set of 15,000 and a test set of 3,000. Each scan in the training set was independently labeled by 3 radiologists, while each scan in the test set was labeled by the consensus of 5 radiologists. We designed and built a labeling platform for DICOM images to facilitate these annotation procedures. All images are made publicly available in DICOM format in company with the labels of the training set. The labels of the test set are hidden at the time of writing this paper as they will be used for benchmarking machine learning algorithms on an open platform.

Mammography, or breast X-ray, is the most widely used imaging modality to detect cancer and other breast diseases. Recent studies have shown that deep learning-based computer-assisted detection and diagnosis (CADe/x) tools have been developed to support physicians and improve the accuracy of interpreting mammography. However, most published datasets of mammography are either limited on sample size or digitalized from screen-film mammography (SFM), hindering the development of CADe/x tools which are developed based on full-field digital mammography (FFDM). To overcome this challenge, we introduce VinDr-Mammo, a new benchmark dataset of FFDM for detecting and diagnosing breast cancer and other diseases in mammography. The dataset consists of 5,000 mammography exams, each of which has four standard views and is double read with disagreement (if any) being resolved by arbitration. It is created for the assessment of Breast Imaging Reporting and Data System (BI-RADS) and density at the breast level. In addition, the dataset also provides the category, location, and BI-RADS assessment of non-benign findings. We make VinDr-Mammo publicly available on https://physionet.org/ as a new imaging resource to promote advances in developing CADe/x tools for breast cancer screening.

PurposeThis article investigates the impact of the growth of the share of various government expenditure programmes in the GDP on economic growth in developing countries while taking into consideration the major issue of potential simultaneity. FindingsBased on data from the World Bank and using two samples of 28 developing economies, we fi nd that per capita GDP growth is dependent upon the growth of per capita public health expenditure in the GDP, growth of per capita public spending on education in the GDP, population growth, growth of the share of total health expenditure in the GDP and the share of gross capital formation in the GDP. Practical implicationsStatistical results of such empirical examination will assist policy-makers in developing countries prioritize their government expenditure in order to stimulate economic growth. Methodology/approachData for all variables are from the World Development Indicators (2008 and 2010). We specify and estimate a simultaneous equations model which consists of two government expenditure growth equations and a GDP growth equation. We observe that some coeffi cient estimates do not have the expected sign due to possible collinearity among some independent variables.

Purpose -This paper aims to examine the impact of the components of human capital on the extent of poverty and income distribution in developing countries. Design/methodology/approach -Data for all variables are from the World Development Report, 2006 and 2007. The least-squares estimation technique in a multivariate linear regression is applied. It is noted that the introduction of interaction terms between income and the components of human capital yields better statistical results, as pointed out in the economic development literature. Findings -Based on data from the World Bank and using a sample of 40 developing economies, it is found that the fraction of the population below the poverty line is linearly dependent upon gender parity ratio in primary and secondary schools, the prevalence of child malnutrition, per capita purchasing power parity gross national income, the maternal mortality rate, and the percentage of births attended by skilled health staff. Using another sample of 35 developing countries, it is found that income inequality linearly depends on the same explanatory variables plus the infant mortality rate and the primary school completion rate. Practical implications -Statistical results of such empirical examination will assist governments in those countries identify areas that need to be improved upon in order to alleviate poverty and improve the distribution of income. Originality/value -This paper provides useful information on the impact of the components of human capital on the extent of poverty and income distribution in developing countries.

This paper investigates the relationship between money, prices, output, and the exchange rate in Bangladesh during the 1974-92 period. Several interesting conclusions can be derived from the paper. First, the inflationary process in Bangladesh cannot be explained exclusively by the monetarist or the structuralist explanation of inflation. Second, regardless of the monetary aggregate employed, monetary policy exerts a significant unidirectional impact on real output. Third, monetary policy and inflation together account for a significant portion of fluctuations in the exchange rate. Finally, it is noted that monetary shocks have a strong, but relatively short-run, impact on inflation. In light of these findings, it can be concluded that monetary policy in Bangladesh should be carried out with extreme caution. While tight money may put a short-term halt to inflation and help stabilize the foreign trade sector, it may also cause a slowdown in the economy.