A clinical microscopy dataset to develop a deep learning diagnostic test for urinary tract infection.

Urinary tract infection (UTI) is a common disorder. Its diagnosis can be made by microscopic examination of voided urine for markers of infection. This manual technique is technically difficult, time-consuming and prone to inter-observer errors. The application of computer vision to this domain has been slow due to the lack of a clinical image dataset from UTI patients. We present an open dataset containing 300 images and 3,562 manually annotated urinary cells labelled into seven classes of clinically significant cell types. It is an enriched dataset acquired from the unstained and untreated urine of patients with symptomatic UTI using a simple imaging system. We demonstrate that this dataset can be used to train a Patch U-Net, a novel deep learning architecture with a random patch generator to recognise urinary cells. Our hope is, with this dataset, UTI diagnosis will be made possible in nearly all clinical settings by using a simple imaging system which leverages advanced machine learning techniques.

The clinical implications of bacterial pathogenesis and mucosal immunity in chronic urinary tract infection.

Urinary tract infections (UTIs) exert a significant health and economic cost globally. Approximately one in four people with a previous history of UTI continue to develop recurrent or chronic infections. Research on UTI has primarily concentrated on pathogen behavior, with the focus gradually shifting to encompass the host immune response. However, these are centered on mouse models of Escherichia coli infection, which may not fully recapitulate the infective etiology and immune responses seen in humans. The emerging field of the urobiome also inadvertently confounds the discrimination of true UTI-causing pathogens from commensals. This review aims to present a novel perspective on chronic UTI by linking microbiology with immunology, which is commonly divergent in this field of research. It also describes the challenges in understanding chronic UTI pathogenesis and the human bladder immune response, largely conjectured from murine studies. Lastly, it outlines the shortcomings of current diagnostic methods in identifying individuals with chronic UTI and consequently treating them, potentially aggravating their disease due to mismanagement of prior episodes. This discourse highlights the need to consider these knowledge gaps and encourages more relevant studies of UTIs in humans.

Mucosal responses of brown-marbled grouper Epinephelus fuscoguttatus (Forsskål, 1775) following intraperitoneal infection with Vibrio harveyi.

Groupers are popular aquaculture species in South-East Asia, but their cultivation is affected by infectious disease outbreaks. Mucosa-associated lymphoid tissues provide a first-line defence against pathogens; however, few studies are available relating to cellular or proteomic responses of mucosal immunity in grouper. Skin, gill and intestine were sampled from brown-marbled grouper Epinephelus fuscoguttatus (Forsskål, 1775) at 4 and 96 hr post-infection (hpi) and 7 days post-infection (dpi) following intraperitoneal infection with Vibrio harveyi, and stained with haematoxylin/eosin and Alcian Blue/periodic acid-Schiff. Skin mucus was analysed by 2D-gel electrophoresis, and proteins modulated by the bacterial infection identified. In the infected fish, significant increases in sacciform cells in skin and increased levels of nucleoside diphosphate kinase in mucus were detected at 4 hpi. At 96 hpi, goblet cells containing acidic mucins significantly increased in the intestine, while those containing mixed mucins increased in skin and gills of infected fish. Proteasome subunit alpha type-I and extracellular Cu/Zn superoxide dismutase levels also increased in mucus. Rodlet and mast cells did not appear to respond to the infection. Mucosal tissues of grouper appeared actively involved in response to Vibrio infection. This information may help future research on improving grouper health, production and vaccine development.