September 12, 2023 Dataset Open Access

Liou, Natasha; De, Trina; Urbanski, Adrian; Khasriya, Rajvinder; Yakimovich, Artur; Horsley, Harry

JSON-LD (schema.org) Export

{
  "@type": "Dataset", 
  "identifier": "https://doi.org/10.14278/rodare.2563", 
  "creator": [
    {
      "affiliation": "Bladder Infection and Immunity Group (BIIG), UCL Centre for Kidney & Bladder Health, Division of Medicine, University College London, Royal Free Hospital Campus, London, United Kingdom", 
      "@id": "https://orcid.org/0000-0002-5644-2604", 
      "name": "Liou, Natasha", 
      "@type": "Person"
    }, 
    {
      "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany; Helmholtz-Zentrum Dresden-Rossendorf e. V. (HZDR), Dresden, Germany", 
      "@id": "https://orcid.org/0000-0003-1111-9851", 
      "name": "De, Trina", 
      "@type": "Person"
    }, 
    {
      "affiliation": "Helmholtz-Zentrum Dresden-Rossendorf e. V. (HZDR), Dresden, Germany; Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany; Institute of Computer Science, University of Wroc\u0142aw, Wroc\u0142aw, Poland", 
      "@id": "https://orcid.org/0009-0008-6619-3665", 
      "name": "Urbanski, Adrian", 
      "@type": "Person"
    }, 
    {
      "affiliation": "Bladder Infection and Immunity Group (BIIG), UCL Centre for Kidney & Bladder Health, Division of Medicine, University College London, Royal Free Hospital Campus, London, United Kingdom", 
      "@id": "https://orcid.org/0000-0002-1696-1442", 
      "name": "Khasriya, Rajvinder", 
      "@type": "Person"
    }, 
    {
      "affiliation": "Center for Advanced Systems Understanding (CASUS), G\u00f6rlitz, Germany; Helmholtz-Zentrum Dresden-Rossendorf e. V. (HZDR), Dresden, Germany; Bladder Infection and Immunity Group (BIIG), UCL Centre for Kidney & Bladder Health, Division of Medicine, University College London, Royal Free Hospital Campus, London, United Kingdom; Institute of Computer Science, University of Wroc\u0142aw, Wroc\u0142aw, Poland", 
      "@id": "https://orcid.org/0000-0003-2458-4904", 
      "name": "Yakimovich, Artur", 
      "@type": "Person"
    }, 
    {
      "affiliation": "Bladder Infection and Immunity Group (BIIG), UCL Centre for Kidney & Bladder Health, Division of Medicine, University College London, Royal Free Hospital Campus, London, United Kingdom", 
      "@id": "https://orcid.org/0000-0002-6967-3321", 
      "name": "Horsley, Harry", 
      "@type": "Person"
    }
  ], 
  "sameAs": [
    "https://www.hzdr.de/publications/Publ-37531"
  ], 
  "distribution": [
    {
      "fileFormat": "zip", 
      "contentUrl": "https://rodare.hzdr.de/api/files/2d96466e-612d-4754-afcc-c65e05fc25da/ds1.zip", 
      "@type": "DataDownload"
    }
  ], 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "url": "https://rodare.hzdr.de/record/2563", 
  "@context": "https://schema.org/", 
  "@id": "https://doi.org/10.14278/rodare.2563", 
  "datePublished": "2023-09-12", 
  "version": "1", 
  "keywords": [
    "clinical microscopy", 
    "urine microscopy", 
    "widefield", 
    "transmission light", 
    "image segmentation", 
    "binary segmentation", 
    "multiclass segmentation"
  ], 
  "name": "Clinical urine microscopy for urinary tract infections", 
  "description": "<p>Urinary tract infections (UTI) are a common disorder. Its diagnosis can be made by microscopic examination of voided urine for cellular markers of infection. We present a dataset containing 300 images and 3,562 manually annotated urinary cells labelled into seven classes of clinically significant urinary content. It is an enriched dataset with samples acquired from the unstained and untreated urine of patients with symptomatic UTI. The aim of the dataset is to facilitate UTI diagnosis in nearly all clinical settings by using a simple imaging system which leverages advanced machine learning techniques.&nbsp;</p>\n\n<p><strong>Data acquisition&nbsp;</strong></p>\n\n<p>300 urine samples were obtained from patients with symptomatic UTI between April and August 2022 from a specialist LUTS outpatient clinic in central London. Urine samples were collected as natural voids and processed on-site within one hour to mitigate cellular degradation. Brightfield microscopic examination (Olympus BX41F microscope frame, U-5RE quintuple nosepiece, U-LS30 LED illuminator, U-AC Abbe condenser) was performed at x20 objective (Olympus PLCN20x Plan C N Achromat 20x/0.4). A disposable haemocytometer (C Chip&trade;) was used for enumeration of red cells (RBC), white cells (WBC), epithelial cells (EPC), and the presence of other cellular content per 1 &micro;l of urine by two experienced microscopists.</p>\n\n<p>Images were acquired using the aforementioned brightfield microscope using a 0.5X C-mount adapter connected to a digital colour camera (Infinity 3S-1UR, Teledyne Lumenera). Images were taken in 16-bit colour in 1392 x 1040 .tif format using Capture and Analyse software. An enriched dataset approach was taken to maximise urinary cellular content in the acquired images. Such data curation was also necessary to overcome class imbalance. Daily Kohler illumination and global white balance was performed to ensure consistency in image acquisition.&nbsp;</p>\n\n<p><strong>Dataset annotation</strong></p>\n\n<p>300 images were acquired and manually annotated by first identifying cells of interest as a binary semantic segmentation task. Individual pixels were dichotomously labelled as either informative cells, foreground, or non-informative background. Non-informative background was further constrained by including unidentifiable cells, such as debris or grossly out-of-focus particles. Binary annotation was initially performed using ilastik, an open-source software using a Random Forest classifier for pixel classification, then manually refined at the pixel level to ensure accurate semantic segmentation. This produced a binary mask in 1392 x 1040 .tif format for each corresponding raw colour image.&nbsp;</p>\n\n<p>Objects of interest were then manually labelled by two expert microscopists into one of seven clinically significant multi-class categories: rods, RBC/WBC, yeast, miscellaneous, single EPC, small EPC sheet, and large EPC sheet. This produced a multi-class mask in 1392 x 1040 .tif format with a label as pixel value from 0-7, where 0 is background (Table 1).&nbsp;</p>\n\n<p><strong>Data structure&nbsp;</strong></p>\n\n<p>The dataset is organised into three root folders: img (image), bin_mask (binary mask), and mult_mask (multi-class mask). Each folder has 300 files in .tif format and labelled with an incremental number.</p>\n\n<p><strong>Table1</strong></p>\n\n<pre><code class=\"language-markdown\">Folder         Files\u00a0       Objects\u00a0              Count       Pixel Values\n\nimg              300        Raw data                                 0-255\nbin_mask\u00a0        300        Background/Foreground                      0/1\nmult_mask\u00a0       300        Background/Class                             0\n                            Rod                    1697                  1\n                            RBC/WBC                1056                  2\n                            Yeast                    41                  3\n                            Miscellaneous\u00a0          550                  4\n                            Single EPC              182                  5\n                            Small EPC sheet          26                  6\n                            Large EPC sheet\u00a0         10                  7\n                                \n                            Total                  3562         </code></pre>", 
  "inLanguage": {
    "name": "English", 
    "alternateName": "eng", 
    "@type": "Language"
  }
}