Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage.
Aneurysmal subarachnoid hemorrhage
Aneurysms
CT angiography
Convolutional neural networks
Deep learning
Journal
Neuroradiology
ISSN: 1432-1920
Titre abrégé: Neuroradiology
Pays: Germany
ID NLM: 1302751
Informations de publication
Date de publication:
Dec 2021
Dec 2021
Historique:
received:
25
01
2021
accepted:
21
03
2021
pubmed:
11
4
2021
medline:
17
11
2021
entrez:
10
4
2021
Statut:
ppublish
Résumé
To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH). Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm In the test set, the detection sensitivity of the DLM-Ens (85.7%) was comparable to the radiologists (reader 1: 91.2%, reader 2: 86.5%, and reader 3: 86.5%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6%, reader 2: 97.6%,and reader 3: 96.0%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2% of the additional aneurysms provided by the DLM). Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.
Identifiants
pubmed: 33837806
doi: 10.1007/s00234-021-02697-9
pii: 10.1007/s00234-021-02697-9
pmc: PMC8589782
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1985-1994Informations de copyright
© 2021. The Author(s).
Références
AJNR Am J Neuroradiol. 2019 Jan;40(1):25-32
pubmed: 30573461
IEEE Trans Med Imaging. 2004 Aug;23(8):983-94
pubmed: 15338732
Lancet Neurol. 2009 Jul;8(7):635-42
pubmed: 19501022
Eur Radiol. 2010 Mar;20(3):549-57
pubmed: 19760237
World Neurosurg. 2017 Jul;103:876-882.e1
pubmed: 28461281
Sci Rep. 2020 Dec 11;10(1):21799
pubmed: 33311535
Neurosurgery. 1999 Dec;45(6):1315-20; discussion 1320-2
pubmed: 10598698
AJNR Am J Neuroradiol. 2004 Oct;25(9):1485-92
pubmed: 15502126
Clin Neuroradiol. 2020 Sep;30(3):591-598
pubmed: 31227844
Brain. 2001 Feb;124(Pt 2):249-78
pubmed: 11157554
J Magn Reson Imaging. 2021 Jan;53(1):259-268
pubmed: 32662130
AJNR Am J Neuroradiol. 2007 Nov-Dec;28(10):1949-55
pubmed: 17898200
Stroke. 2003 Jan;34(1):16-21
pubmed: 12511744
Radiology. 2019 Jan;290(1):187-194
pubmed: 30351253
Radiology. 2017 Aug;284(2):574-582
pubmed: 28436741
Int J Comput Assist Radiol Surg. 2020 Apr;15(4):715-723
pubmed: 32056126
Stroke. 2013 Sep;44(9):2414-21
pubmed: 23868274
J Neuroradiol. 2007 Oct;34(4):243-9
pubmed: 17761283
Med Image Anal. 2017 Feb;36:61-78
pubmed: 27865153
Stroke. 2013 Jan;44(1):29-37
pubmed: 23238862
Radiology. 2009 Sep;252(3):808-15
pubmed: 19508992
Lancet. 2007 Jan 27;369(9558):306-18
pubmed: 17258671
Insights Imaging. 2017 Feb;8(1):171-182
pubmed: 27928712
JAMA Netw Open. 2019 Jun 5;2(6):e195600
pubmed: 31173130
Lancet. 2002 Oct 26;360(9342):1267-74
pubmed: 12414200
Radiographics. 2015 Oct;35(6):1668-76
pubmed: 26466178
AJNR Am J Neuroradiol. 2021 Apr;42(4):655-662
pubmed: 33541907
Radiology. 2004 Feb;230(2):510-8
pubmed: 14699177
Neuroimage. 2005 Jul 1;26(3):839-51
pubmed: 15955494
Radiology. 2018 Apr;287(1):313-322
pubmed: 29095675
Radiology. 2021 Jan;298(1):155-163
pubmed: 33141003
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571
Nat Commun. 2020 Nov 30;11(1):6090
pubmed: 33257700
Lancet Oncol. 2019 May;20(5):728-740
pubmed: 30952559