A transfer learning approach to identify Plasmodium in microscopic images.

Plasmodium parasites cause Malaria disease, which remains a significant threat to global health, affecting 200 million people and causing 400,000 deaths yearly. Plasmodium falciparum and Plasmodium vivax remain the two main malaria species affecting humans. Identifying the malaria disease in blood smears requires years of expertise, even for highly trained specialists. Literature studies have been coping with the automatic identification and classification of malaria. However, several points must be addressed and investigated so these automatic methods can be used clinically in a Computer-aided Diagnosis (CAD) scenario. In this work, we assess the transfer learning approach by using well-known pre-trained deep learning architectures. We considered a database with 6222 Region of Interest (ROI), of which 6002 are from the Broad Bioimage Benchmark Collection (BBBC), and 220 were acquired locally by us at Fundação Oswaldo Cruz (FIOCRUZ) in Porto Velho Velho, Rondônia-Brazil, which is part of the legal Amazon. We exhaustively cross-validated the dataset using 100 distinct partitions with 80% train and 20% test for each considering circular ROIs (rough segmentation). Our experimental results show that DenseNet201 has a potential to identify Plasmodium parasites in ROIs (infected or uninfected) of microscopic images, achieving 99.41% AUC with a fast processing time. We further validated our results, showing that DenseNet201 was significantly better (99% confidence interval) than the other networks considered in the experiment. Our results support claiming that transfer learning with texture features potentially differentiates subjects with malaria, spotting those with Plasmodium even in Leukocytes images, which is a challenge. In Future work, we intend scale our approach by adding more data and developing a friendly user interface for CAD use. We aim at aiding the worldwide population and our local natives living nearby the legal Amazon's rivers.

Antibiotic resistance and biofilm formation in children with Enteropathogenic Escherichia coli (EPEC) in Brazilian Amazon.

INTRODUCTION: Enteropathogenic Escherichia coli is an important causative agent of diarrhea in both developed and developing countries. METHODOLOGY: We assessed the antibiotic resistance profile and the ability of 71 Enteropathogenic Escherichia coli (EPEC) isolates from children in the age group 6 years, or younger, to form biofilm. These children were hospitalized in Cosme and Damião Children Hospital in Porto Velho, Western Brazilian Amazon, between 2010 and 2012, with clinical symptoms of acute gastroenteritis. RESULTS: The highest frequency of atypical EPEC (aEPEC) isolates reached 83.1% (59/71). Most EPEC isolates presented Localized Adherence Like (LAL) pattern in HEp-2 cells (57.7% - 41/71). Biofilm production was observed in 33.8% (24/71) of EPEC isolates, and it means statistically significant association with shf gene (p = 0.0254). The highest antimicrobial resistance rates and a large number of multiresistant isolates 67.6% (48/71), regarded cefuroxime (CXM), ampicillin (AMP), trimethoprim-sulfamethoxazole (SXT) and tetracycline (TET), respectively, mainly in typical EPEC (tEPEC). Furthermore, 96% (68/71) of EPEC isolates in the present study were resistant to at least one antibiotic, whereas only 3 isolates were sensitive to all the tested drugs. CONCLUSION: Based on our findings, there was increased aEPEC identification. EPEC isolates showed high resistance rate; most strains showed multiresistance; thus, they work as warning about the continuous need of surveillance towards antimicrobial use. Besides, the ability of forming biofilm was evidenced by the EPEC isolates. This outcome is worrisome, since it is a natural resistance mechanism of bacteria.