A clinical microscopy dataset to develop a deep learning diagnostic test for urinary tract infection.
Journal
Scientific data
ISSN: 2052-4463
Titre abrégé: Sci Data
Pays: England
ID NLM: 101640192
Informations de publication
Date de publication:
01 Feb 2024
01 Feb 2024
Historique:
received:
21
09
2023
accepted:
16
01
2024
medline:
2
2
2024
pubmed:
2
2
2024
entrez:
1
2
2024
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 38302487
doi: 10.1038/s41597-024-02975-0
pii: 10.1038/s41597-024-02975-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
155Informations de copyright
© 2024. The Author(s).
Références
Foxman, B. Epidemiology of urinary tract infections: incidence, morbidity, and economic costs. Am J Med 113(Suppl 1A), 5S–13S, https://doi.org/10.1016/s0002-9343(02)01054-9 (2002).
doi: 10.1016/s0002-9343(02)01054-9
pubmed: 12113866
Hooton, T. M. Recurrent urinary tract infection in women. Int J Antimicrob Agents 17, 259–268, https://doi.org/10.1016/s0924-8579(00)00350-2 (2001).
doi: 10.1016/s0924-8579(00)00350-2
pubmed: 11295405
NHS could slash emergency admission costs with better use of medical technology. The Medical Technology Group https://www.mtg.org.uk/wp-content/uploads/2016/07/Admissions-of-Failure-report-release-FINAL-131115-1.pdf (2015).
Lodise, T. P., Chopra, T., Nathanson, B. H. & Sulham, K. Hospital admission patterns of adult patients with complicated urinary tract infections who present to the hospital by disease acuity and comorbid conditions: How many admissions are potentially avoidable? Am J Infect Control 49, 1528–1534, https://doi.org/10.1016/j.ajic.2021.05.013 (2021).
doi: 10.1016/j.ajic.2021.05.013
pubmed: 34077786
Simmering, J. E., Tang, F., Cavanaugh, J. E., Polgreen, L. A. & Polgreen, P. M. The Increase in Hospitalizations for Urinary Tract Infections and the Associated Costs in the United States, 1998-2011. Open Forum Infect Dis 4, ofw281, https://doi.org/10.1093/ofid/ofw281 (2017).
doi: 10.1093/ofid/ofw281
pubmed: 28480273
pmcid: 5414046
Kost, G. J. Principles & practice of point-of-care testing. (Lippincott Williams & Wilkins, 2002).
Khasriya, R. et al. The inadequacy of urinary dipstick and microscopy as surrogate markers of urinary tract infection in urological outpatients with lower urinary tract symptoms without acute frequency and dysuria. J Urol 183, 1843–1847, https://doi.org/10.1016/j.juro.2010.01.008 (2010).
doi: 10.1016/j.juro.2010.01.008
pubmed: 20303096
Brubaker, L. et al. Tarnished Gold-the” Standard” Urine Culture: Reassessing the characteristics of a criterion standard for detecting urinary microbes. Frontiers in Urology 3, 1206046.
Chieng, C. C. Y., Kong, Q., Liou, N. S. Y., Khasriya, R. & Horsley, H. The clinical implications of bacterial pathogenesis and mucosal immunity in chronic urinary tract infection. Mucosal Immunol 16, 61–71, https://doi.org/10.1016/j.mucimm.2022.12.003 (2023).
doi: 10.1016/j.mucimm.2022.12.003
pubmed: 36642381
Latham, R. H., Wong, E. S., Larson, A., Coyle, M. & Stamm, W. E. Laboratory diagnosis of urinary tract infection in ambulatory women. JAMA 254, 3333–3336 (1985).
doi: 10.1001/jama.1985.03360230065024
pubmed: 3906157
Kupelian, A. S. et al. Discrediting microscopic pyuria and leucocyte esterase as diagnostic surrogates for infection in patients with lower urinary tract symptoms: results from a clinical and laboratory evaluation. BJU Int 112, 231–238, https://doi.org/10.1111/j.1464-410X.2012.11694.x (2013).
doi: 10.1111/j.1464-410X.2012.11694.x
pubmed: 23305196
Wu, J., Miao, Y. & Abraham, S. N. The multiple antibacterial activities of the bladder epithelium. Ann Transl Med 5, 35, https://doi.org/10.21037/atm.2016.12.71 (2017).
doi: 10.21037/atm.2016.12.71
pubmed: 28217700
pmcid: 5300852
Mulvey, M. A. et al. Induction and evasion of host defenses by type 1-piliated uropathogenic Escherichia coli. Science 282, 1494–1497, https://doi.org/10.1126/science.282.5393.1494 (1998).
doi: 10.1126/science.282.5393.1494
pubmed: 9822381
Choi, H. W. et al. Loss of Bladder Epithelium Induced by Cytolytic Mast Cell Granules. Immunity 45, 1258–1269, https://doi.org/10.1016/j.immuni.2016.11.003 (2016).
doi: 10.1016/j.immuni.2016.11.003
pubmed: 27939674
pmcid: 5177478
Khasriya, R. et al. Lower urinary tract symptoms that predict microscopic pyuria. Int Urogynecol J 29, 1019–1028, https://doi.org/10.1007/s00192-017-3472-7 (2017).
doi: 10.1007/s00192-017-3472-7
pubmed: 28971220
pmcid: 6004270
Goswami, D., Aggrawal, H. O., Gupta, R. & Agarwal, V. Urine microscopic image dataset. arXiv preprint arXiv:2111.10374 (2021).
Sokolov, I. et al. Noninvasive diagnostic imaging using machine-learning analysis of nanoresolution images of cell surfaces: Detection of bladder cancer. Proc Natl Acad Sci USA 115, 12920–12925, https://doi.org/10.1073/pnas.1816459115 (2018).
doi: 10.1073/pnas.1816459115
pubmed: 30509988
pmcid: 6304950
Sanghvi, A. B., Allen, E. Z., Callenberg, K. M. & Pantanowitz, L. Performance of an artificial intelligence algorithm for reporting urine cytopathology. Cancer Cytopathol 127, 658–666, https://doi.org/10.1002/cncy.22176 (2019).
doi: 10.1002/cncy.22176
pubmed: 31412169
Edelstein, A. D. et al. Advanced methods of microscope control using muManager software. J Biol Methods 1, https://doi.org/10.14440/jbm.2014.36 (2014).
Berg, S. et al. ilastik: interactive machine learning for (bio) image analysis. Nat Methods 16, 1226–1232, https://doi.org/10.1038/s41592-019-0582-9 (2019).
doi: 10.1038/s41592-019-0582-9
pubmed: 31570887
Takeuchi, S., DiLuzio, W. R., Weibel, D. B. & Whitesides, G. M. Controlling the shape of filamentous cells of Escherichia coli. Nano Lett 5, 1819–1823, https://doi.org/10.1021/nl0507360 (2005).
doi: 10.1021/nl0507360
pubmed: 16159230
pmcid: 2519610
Justice, S. S., Hunstad, D. A., Seed, P. C. & Hultgren, S. J. Filamentation by Escherichia coli subverts innate defenses during urinary tract infection. Proc Natl Acad Sci USA 103, 19884–19889, https://doi.org/10.1073/pnas.0606329104 (2006).
doi: 10.1073/pnas.0606329104
pubmed: 17172451
pmcid: 1750882
Weinstein, R. A., Lundstrom, T. & Sobel, J. Nosocomial candiduria: a review. Clinical infectious diseases 32, 1602–1607 (2001).
doi: 10.1086/320531
Stamm, W. E. Criteria for the diagnosis of urinary tract infection and for the assessment of therapeutic effectiveness. Infection 20 Suppl 3, S151–154; discussion S160-151, https://doi.org/10.1007/BF01704358 (1992).
Wallmark, G., Arremark, I. & Telander, B. Staphylococcus saprophyticus: a frequent cause of acute urinary tract infection among female outpatients. J Infect Dis 138, 791–797, https://doi.org/10.1093/infdis/138.6.791 (1978).
doi: 10.1093/infdis/138.6.791
pubmed: 739158
Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lect Notes Comput Sc 9351, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28 (2015).
doi: 10.1007/978-3-319-24574-4_28
Wang, C., Zhao, Z., Ren, Q., Xu, Y. & Yu, Y. Dense U-net based on patch-based learning for retinal vessel segmentation. Entropy 21, 168 (2019).
doi: 10.3390/e21020168
pubmed: 33266884
pmcid: 7514650
Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance normalization: The missing ingredient for fast stylization. CoRR abs/1607.08022 (2016).
Fukushima, K. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36, 193–202, https://doi.org/10.1007/BF00344251 (1980).
doi: 10.1007/BF00344251
pubmed: 7370364
Ioffe, S. & Szegedy, C. in International conference on machine learning. 448–456 (pmlr).
Shannon, C. E. A mathematical theory of communication. The Bell system technical journal 27, 379–423 (1948).
doi: 10.1002/j.1538-7305.1948.tb01338.x
Sorensen, T. A. A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. Biol. Skar. 5, 1–34 (1948).
Dice, L. R. Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945).
doi: 10.2307/1932409
Verhulst, P.-F. Notice sur la loi que la population suit dans son accroissement. Correspondence mathematique et physique 10, 113–129 (1838).
Sinharay, S. in International Encyclopedia of Education (Fourth Edition) (eds Tierney, Robert J., Rizvi, Fazal & Ercikan, Kadriye) 718–722 (Elsevier, 2023).
Jaccard, P. The distribution of the flora in the alpine zone. 1. New phytologist 11, 37–50 (1912).
doi: 10.1111/j.1469-8137.1912.tb05611.x
Allen, K., Berry, M. M., Luehrs, F. U. Jr & Perry, J. W. Machine literature searching VIII. Operational criteria for designing information retrieval systems. American Documentation (pre-1986) 6, 93 (1955).
doi: 10.1002/asi.5090060209
Peterson, W., Birdsall, T. & Fox, W. The theory of signal detectability. Transactions of the IRE professional group on information theory 4, 171–212 (1954).
doi: 10.1109/TIT.1954.1057460
Woodward, P. Probability and information theory, with applications to radar. (London: Pergamon Press Ltd. First published, 1953).
Kingma, D. P. & Ba, J. L. in Proceedings of the 3rd International Conference for Learning Representations (ICLR ’15) (San Diego, 2015).
Plaut, D. C. Experiments on Learning by Back Propagation. (1986).
Liou, N. et al. Clinical urine microscopy for urinary tract infections. Rodare https://doi.org/10.14278/rodare.2473 (2023).
Li, A.-C. et al. Patch-based U-net model for isotropic quantitative differential phase contrast imaging. IEEE Transactions on Medical Imaging 40, 3229–3237 (2021).
doi: 10.1109/TMI.2021.3091207
pubmed: 34152982
de Amorim, L. B., Cavalcanti, G. D. & Cruz, R. M. The choice of scaling technique matters for classification performance. Applied Soft Computing 133, 109924 (2023).
doi: 10.1016/j.asoc.2022.109924
Raju, V. G., Lakshmi, K. P., Jain, V. M., Kalidindi, A. & Padma, V. in 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT). 729–735 (IEEE).