Residential scene classification for gridded population sampling in developing countries using deep convolutional neural networks on satellite imagery.

Background: Conducting surveys in low- and middle-income countries is often challenging because many areas lack a complete sampling frame, have outdated census information, or have limited data available for designing and selecting a representative sample. Geosampling is a probability-based, gridded population sampling method that addresses some of these issues by using geographic information system (GIS) tools to create logistically manageable area units for sampling. GIS grid cells are overlaid to partition a country's existing administrative boundaries into area units that vary in size from 50 m × 50 m to 150 m × 150 m.

Evaluation of different laboratory methods for rapid diagnosis of tuberculous pleurisy.

Background/objective: Tuberculous pleurisy is a diagnostic challenge due to its nonspecific clinical presentation, paucibacillary nature of the effusion together with the inefficiency of conventional laboratory methods motivating the evaluation of variable diagnostic strategies.

Methods: Using thoracoscopy, the pleural cavity of 50 patients with undiagnosed exudative pleural effusion were fully examined and biopsy specimens of affected parietal pleura were taken under direct vision. Pleural fluid and biopsy specimen were subjected to microscopic examination (direct and after cytocentrifugation), culture, PCR, and histopathological examination.