Automated evaluation of probe-based confocal laser endomicroscopy in the lung.
Aged
Algorithms
Automation
Bronchoscopy
/ methods
Computer Systems
Elastin
/ analysis
Equipment Design
Female
Humans
Image Processing, Computer-Assisted
Lung Diseases, Interstitial
/ pathology
Male
Microscopy, Confocal
/ instrumentation
Microscopy, Video
/ instrumentation
Middle Aged
Non-Smokers
Pulmonary Alveoli
/ chemistry
Smoking Cessation
Supervised Machine Learning
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2020
2020
Historique:
received:
06
02
2020
accepted:
22
04
2020
entrez:
7
5
2020
pubmed:
7
5
2020
medline:
6
8
2020
Statut:
epublish
Résumé
Probe-based confocal endomicroscopy provides real time videos of autoflourescent elastin structures within the alveoli. With it, multiple changes in the elastin structure due to different diffuse parenchymal lung diseases have previously been described. However, these evaluations have mainly relied on qualitative evaluation by the examiner and manually selected parts post-examination. To develop a fully automatic method for quantifying structural properties of the imaged alveoli elastin and to perform a preliminary assessment of their diagnostic potential. 46 patients underwent probe-based confocal endomicroscopy, of which 38 were divided into 4 groups categorizing different diffuse parenchymal lung diseases. 8 patients were imaged in representative healthy lung areas and used as control group. Alveolar elastin structures were automatically segmented with a trained machine learning algorithm and subsequently evaluated with two methods developed for quantifying the local thickness and structural connectivity. The automatic segmentation algorithm performed generally well and all 4 patient groups showed statistically significant differences with median elastin thickness, standard deviation of thickness and connectivity compared to the control group. Alveoli elastin structures can be quantified based on their structural connectivity and thickness statistics with a fully-automated algorithm and initial results highlight its potential for distinguishing parenchymal lung diseases from normal alveoli.
Identifiants
pubmed: 32374768
doi: 10.1371/journal.pone.0232847
pii: PONE-D-20-03450
pmc: PMC7202624
doi:
Substances chimiques
ELN protein, human
0
Elastin
9007-58-3
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0232847Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Am J Respir Crit Care Med. 2012 Jun 1;185(11):1147-53
pubmed: 22366047
Respir Res. 2011 Jun 23;12(1):85
pubmed: 21699692
Respiration. 2018;95(3):188-200
pubmed: 29316560
Am J Respir Crit Care Med. 2004 Oct 15;170(8):904-10
pubmed: 15256390
BMJ. 1998 Apr 18;316(7139):1236-8
pubmed: 9553006
J Heart Lung Transplant. 2014 May;33(5):492-8
pubmed: 24656287
Lancet Respir Med. 2017 Jan;5(1):61-71
pubmed: 27932290
Lung Cancer. 2007 Oct;58(1):44-9
pubmed: 17532537
Am J Respir Crit Care Med. 2011 Mar 15;183(6):788-824
pubmed: 21471066
Am J Respir Crit Care Med. 2007 Jan 1;175(1):22-31
pubmed: 17023733
J Thorac Dis. 2016 Dec;8(12):3505-3514
pubmed: 28149543
IEEE Trans Pattern Anal Mach Intell. 2005 Aug;27(8):1226-38
pubmed: 16119262
J Bronchology Interv Pulmonol. 2011 Jan;18(1):23-30
pubmed: 23169014
Am J Respir Crit Care Med. 2018 Apr 1;197(7):947-948
pubmed: 29394081
Am J Respir Crit Care Med. 2013 Jul 15;188(2):141-9
pubmed: 23672718
Bioinformatics. 2017 Aug 1;33(15):2424-2426
pubmed: 28369169
BMJ. 1995 Jan 21;310(6973):170
pubmed: 7833759
Nat Methods. 2012 Jun 28;9(7):676-82
pubmed: 22743772
Lung Cancer. 2007 Jun;56(3):295-302
pubmed: 17291623
Respiration. 2010;79(6):441-9
pubmed: 20431326
Respiration. 2019;97(3):259-263
pubmed: 30428462
Respirology. 2019 Aug;24(8):783-791
pubmed: 30811085
Respir Med. 2013 Aug;107(8):1234-40
pubmed: 23706778
Respir Med. 2012 Jan;106(1):127-37
pubmed: 22000588
Lancet Respir Med. 2018 Feb;6(2):138-153
pubmed: 29154106