Automatic Bacillus Detection in Light Field Microscopy Images Using Convolutional Neural Networks and Mosaic Imaging Approach.

Tuberculosis (TB) is one of the top 10 causes of death worldwide. The diagnosis and treatment of TB in its early stages is fundamental to reducing the rate of people affected by this disease. In order to assist specialists in the diagnosis in bright field smear images, many studies have been developed for the automatic Mycobacterium tuberculosis detection, the causative agent of Tb. To contribute to this theme, a method to bacilli detection associating convolutional neural network (CNN) and a mosaic-image approach was implemented. The propose was evaluated using a robust image dataset validated by three specialists. Three CNN architectures and 3 optimization methods in each architecture were evaluated. The deeper architecture presented better results, reaching accuracies values above 99%. Other metrics like precision, sensitivity, specificity and F1-score were also used to assess the CNN models performance.

Inflammasome genetics contributes to the development and control of active pulmonary tuberculosis.

Tuberculosis (TB) continues to be a major public health problem. An estimated one-third of the world's population is infected with Mycobacterium tuberculosis (Mtb) but remains asymptomatic (latent TB) and only 5% to 10% of these latent individuals will develop active pulmonary TB. Factors affecting the balance between latent and active TB are mostly unknown, even if host genome has been shown to contribute to the outcome of Mtb response. Acute inflammation and Th1 response are important in the early clearance of the bacteria as it was emphasized by the association between immune genes (i.e.: HLA, IFNG, TNF, NRPAM1, IL10) variants and the development of active pulmonary TB. Recently, the role of the inflammasome in experimental TB has been demonstrated, however, to our knowledge, no data still exist about the contribution of inflammasome genetics to Mtb susceptibility and/or to the development of active TB. For this reason, selected polymorphisms in inflammasome genes were analysed in a case/control cohort of individuals with active pulmonary TB from an endemic area of Brazil Amazon. Our data evidence the novel association between polymorphisms in NLRP3-inflammasome encoding genes and active pulmonary TB, and replicated the association between P2X7 and TB observed in other populations. These results emphasize the role of NLRP3-inflammasome also in human TB, and contribute to our knowledge about pathways involved in the development of active TB, even if deeper investigation are needed to fully elucidate the role of the complex in Mtb infection.