Performance of deep learning to detect mastoiditis using multiple conventional radiographs of mastoid.
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:
23
04
2020
accepted:
20
10
2020
entrez:
11
11
2020
pubmed:
12
11
2020
medline:
21
1
2021
Statut:
epublish
Résumé
This study aimed to compare the diagnostic performance of deep learning algorithm trained by single view (anterior-posterior (AP) or lateral view) with that trained by multiple views (both views together) in diagnosis of mastoiditis on mastoid series and compare the diagnostic performance between the algorithm and radiologists. Total 9,988 mastoid series (AP and lateral views) were classified as normal or abnormal (mastoiditis) based on radiographic findings. Among them 792 image sets with temporal bone CT were classified as the gold standard test set and remaining sets were randomly divided into training (n = 8,276) and validation (n = 920) sets by 9:1 for developing a deep learning algorithm. Temporal (n = 294) and geographic (n = 308) external test sets were also collected. Diagnostic performance of deep learning algorithm trained by single view was compared with that trained by multiple views. Diagnostic performance of the algorithm and two radiologists was assessed. Inter-observer agreement between the algorithm and radiologists and between two radiologists was calculated. Area under the receiver operating characteristic curves of algorithm using multiple views (0.971, 0.978, and 0.965 for gold standard, temporal, and geographic external test sets, respectively) showed higher values than those using single view (0.964/0.953, 0.952/0.961, and 0.961/0.942 for AP view/lateral view of gold standard, temporal external, and geographic external test sets, respectively) in all test sets. The algorithm showed statistically significant higher specificity compared with radiologists (p = 0.018 and 0.012). There was substantial agreement between the algorithm and two radiologists and between two radiologists (κ = 0.79, 0.8, and 0.76). The deep learning algorithm trained by multiple views showed better performance than that trained by single view. The diagnostic performance of the algorithm for detecting mastoiditis on mastoid series was similar to or higher than that of radiologists.
Identifiants
pubmed: 33176335
doi: 10.1371/journal.pone.0241796
pii: PONE-D-20-11571
pmc: PMC7657495
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0241796Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Biochem Med (Zagreb). 2012;22(3):276-82
pubmed: 23092060
Radiology. 2017 Aug;284(2):574-582
pubmed: 28436741
Ann Otol Rhinol Laryngol. 2005 Feb;114(2):147-52
pubmed: 15757196
Eur Arch Otorhinolaryngol. 2014 May;271(5):925-31
pubmed: 23589156
Radiology. 2020 Feb;294(2):342-350
pubmed: 31891320
Radiology. 1985 May;155(2):391-7
pubmed: 3983389
Acta Otolaryngol. 1987 Mar-Apr;103(3-4):226-31
pubmed: 3577754
Eur Radiol. 2020 Feb;30(2):1243-1253
pubmed: 31468158
J Magn Reson Imaging. 2020 Jan;51(1):175-182
pubmed: 31050074
Bioinformatics. 2014 Jun 15;30(12):i121-9
pubmed: 24931975
Thyroid. 2018 Oct;28(10):1332-1338
pubmed: 30132411
Otol Neurotol. 2008 Sep;29(6):751-7
pubmed: 18617870
J Thorac Imaging. 2019 Mar;34(2):75-85
pubmed: 30802231
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149
pubmed: 27295650
JAMA. 2016 Dec 13;316(22):2402-2410
pubmed: 27898976
Radiology. 2019 Oct;293(1):38-46
pubmed: 31385754
Eur Radiol. 2019 Dec;29(12):6891-6899
pubmed: 31264017
Ann Otol Rhinol Laryngol. 2001 May;110(5 Pt 1):486-90
pubmed: 11372935
J Am Coll Radiol. 2017 Mar;14(3):337-342
pubmed: 27927591
PLoS One. 2018 Oct 4;13(10):e0204155
pubmed: 30286097
Head Neck. 2019 Apr;41(4):885-891
pubmed: 30715773
J Laryngol Otol. 2003 Aug;117(8):595-8
pubmed: 12956911
Quant Imaging Med Surg. 2019 Jun;9(6):942-951
pubmed: 31367548
Invest Radiol. 2019 Jan;54(1):7-15
pubmed: 30067607
AJNR Am J Neuroradiol. 2007 Mar;28(3):493-6
pubmed: 17353320
Surg Radiol Anat. 2005 Mar;27(1):37-42
pubmed: 15349696
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Rom J Morphol Embryol. 2009;50(3):453-60
pubmed: 19690774