Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
28 10 2023
28 10 2023
Historique:
received:
26
11
2022
accepted:
13
10
2023
medline:
30
10
2023
pubmed:
29
10
2023
entrez:
29
10
2023
Statut:
epublish
Résumé
Full Laboratory Automation is revolutionizing work habits in an increasing number of clinical microbiology facilities worldwide, generating huge streams of digital images for interpretation. Contextually, deep learning architectures are leading to paradigm shifts in the way computers can assist with difficult visual interpretation tasks in several domains. At the crossroads of these epochal trends, we present a system able to tackle a core task in clinical microbiology, namely the global interpretation of diagnostic bacterial culture plates, including presumptive pathogen identification. This is achieved by decomposing the problem into a hierarchy of complex subtasks and addressing them with a multi-network architecture we call DeepColony. Working on a large stream of clinical data and a complete set of 32 pathogens, the proposed system is capable of effectively assist plate interpretation with a surprising degree of accuracy in the widespread and demanding framework of Urinary Tract Infections. Moreover, thanks to the rich species-related generated information, DeepColony can be used for developing trustworthy clinical decision support services in laboratory automation ecosystems from local to global scale.
Identifiants
pubmed: 37898607
doi: 10.1038/s41467-023-42563-1
pii: 10.1038/s41467-023-42563-1
pmc: PMC10613199
doi:
Banques de données
figshare
['10.6084/m9.figshare.24203961']
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
6874Informations de copyright
© 2023. The Author(s).
Références
Clin Microbiol Infect. 2015 May;21(5):404-15
pubmed: 25964152
Nat Rev Microbiol. 2015 May;13(5):269-84
pubmed: 25853778
Ann Lab Med. 2013 Jan;33(1):14-27
pubmed: 23301218
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
J Clin Microbiol. 2016 Oct;54(10):2424-6
pubmed: 27510833
Nat Mach Intell. 2021 Sep;3(9):738-739
pubmed: 34604702
Nature. 2016 Jan 28;529(7587):484-9
pubmed: 26819042
Clin Microbiol Infect. 2020 Oct;26(10):1324-1331
pubmed: 32603804
J Clin Microbiol. 2021 Feb 18;59(3):
pubmed: 33239383
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Nature. 2016 Jan 21;529(7586):336-43
pubmed: 26791724
Theriogenology. 2010 Jun;73(9):1167-79
pubmed: 20138353
Clin Infect Dis. 2009 Aug 15;49(4):543-51
pubmed: 19583519
J Clin Microbiol. 2015 May;53(5):1467-72
pubmed: 25253793
Am J Clin Pathol. 2019 Jul 5;152(2):155-168
pubmed: 31135889
Clin Microbiol Rev. 2014 Oct;27(4):783-822
pubmed: 25278575
Clin Microbiol Infect. 2016 Jan;22(1):12-21
pubmed: 26493844
J Clin Microbiol. 2016 Nov;54(11):2841
pubmed: 27582515
Nat Commun. 2019 Oct 30;10(1):4927
pubmed: 31666527
J Biomed Inform. 2021 Jan;113:103655
pubmed: 33309898
Nature. 2008 Feb 21;451(7181):990-3
pubmed: 18288193
Arch Pathol Lab Med. 2017 Nov;141(11):1540-1543
pubmed: 28758790
Nat Rev Genet. 2012 Sep;13(9):601-612
pubmed: 22868263
J Clin Microbiol. 2013 Jun;51(6):1658-65
pubmed: 23515547
FEMS Microbiol Rev. 2012 Mar;36(2):380-407
pubmed: 22092265
J Clin Microbiol. 2014 Sep;52(9):3140-6
pubmed: 24648549
Artif Intell Rev. 2023;56(2):1013-1070
pubmed: 35528112
Clin Microbiol Infect. 2016 Mar;22(3):236-43
pubmed: 26577142
Clin Microbiol Rev. 2014 Oct;27(4):1025-47
pubmed: 25278581
Clin Chem. 2019 May;65(5):634-643
pubmed: 30518664
J Pathol Inform. 2015 May 28;6:23
pubmed: 26110091
J Clin Microbiol. 2016 Oct;54(10):2464-9
pubmed: 27413193