An End-to-End System for Automatic Urinary Particle Recognition with Convolutional Neural Network.

The urine sediment analysis of particles in microscopic images can assist physicians in evaluating patients with renal and urinary tract diseases. Manual urine sediment examination is labor-intensive, subjective and time-consuming, and the traditional automatic algorithms often extract the hand-crafted features for recognition. Instead of using the hand-crafted features, in this paper we propose to exploit convolutional neural network (CNN) to learn features in an end-to-end manner to recognize the urinary particle. We treat the urinary particle recognition as object detection and exploit two state-of-the-art CNN-based object detection methods, Faster R-CNN and single shot multibox detector (SSD), along with their variants for urinary particle recognition. We further investigate different factors involving these CNN-based methods to improve the performance of urinary particle recognition. We comprehensively evaluate these methods on a dataset consisting of 5,376 annotated images corresponding to 7 categories of urinary particle, i.e., erythrocyte, leukocyte, epithelial cell, crystal, cast, mycete, epithelial nuclei, and obtain a best mean average precision (mAP) of 84.1% while taking only 72 ms per image on a NVIDIA Titan X GPU.

Study of drug resistance and molecular typing of 59 cholerae01 clinical isolates from 1984 to 2002 in Chongqing, China.

OBJECTIVE: To analyze the correlation between drug resistance and Cholerae01 clinical isolates from 1984 to 2002 in Chongqing, China. METHODS: K-B assay was applied to detect the sensitivity of 59 Cholerae01 clinical isolates (20 Ogawa, 39 Inaba) to 16 kinds of antibiotics. BioNumerics software was used for a cluster analysis of electrophoresis patterns obtained from the Not I enzyme-cutting genomic DNA by Pulsed-field gel electrophoresis (PFGE). RESULTS: Vibrio cholerae01 in Chongqing area, China were highly resistant to Cotrimoxazole, Furazolidone and Streptomycin. The resistance rates were 28.81% (17/59), 61.02% (36/59) and 30.51% (18/59), respectively. While the isolates from the crowd were sensitive to Amikacin, Gentamicin, Tobramycin, Ampicillin, Neomycin and Doxycycline, and no drug-resistant strains were observed. CONCLUSION: No significant changes are found in the drug resistance of Vibrio cholerae01 from the crowd in Chongqing, China and the drug resistances of the Ogawa and the Inaba strains are different. Vibrio cholerae01 from the crowd in Chongqing, China are highly homologous, which may be from the epidemic strains with the same source.