Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Tytuł pozycji:

Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage.

Tytuł:
Deep learning assistance increases the detection sensitivity of radiologists for secondary intracranial aneurysms in subarachnoid hemorrhage.
Autorzy:
Pennig L; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany. .
Hoyer UCI; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.
Krauskopf A; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany.
Shahzad R; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Innovative Technologies, Philips Healthcare, Aachen, Germany.
Jünger ST; Center for Neurosurgery, Department of General Neurosurgery, University of Cologne, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany.
Thiele F; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Innovative Technologies, Philips Healthcare, Aachen, Germany.
Laukamp KR; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.
Grunz JP; Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany.
Perkuhn M; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Innovative Technologies, Philips Healthcare, Aachen, Germany.
Schlamann M; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.
Kabbasch C; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.
Borggrefe J; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Bochum, Germany.
Goertz L; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.; Center for Neurosurgery, Department of General Neurosurgery, University of Cologne, Faculty of Medicine and University Hospital, University of Cologne, Cologne, Germany.
Źródło:
Neuroradiology [Neuroradiology] 2021 Dec; Vol. 63 (12), pp. 1985-1994. Date of Electronic Publication: 2021 Apr 10.
Typ publikacji:
Journal Article
Język:
English
Imprint Name(s):
Original Publication: Berlin, New York, Springer-Verlag.
MeSH Terms:
Deep Learning*
Intracranial Aneurysm*/diagnostic imaging
Subarachnoid Hemorrhage*/diagnostic imaging
Angiography, Digital Subtraction ; Cerebral Angiography ; Humans ; Radiologists ; Sensitivity and Specificity
References:
AJNR Am J Neuroradiol. 2019 Jan;40(1):25-32. (PMID: 30573461)
IEEE Trans Med Imaging. 2004 Aug;23(8):983-94. (PMID: 15338732)
Lancet Neurol. 2009 Jul;8(7):635-42. (PMID: 19501022)
Eur Radiol. 2010 Mar;20(3):549-57. (PMID: 19760237)
World Neurosurg. 2017 Jul;103:876-882.e1. (PMID: 28461281)
Sci Rep. 2020 Dec 11;10(1):21799. (PMID: 33311535)
Neurosurgery. 1999 Dec;45(6):1315-20; discussion 1320-2. (PMID: 10598698)
AJNR Am J Neuroradiol. 2004 Oct;25(9):1485-92. (PMID: 15502126)
Clin Neuroradiol. 2020 Sep;30(3):591-598. (PMID: 31227844)
Brain. 2001 Feb;124(Pt 2):249-78. (PMID: 11157554)
J Magn Reson Imaging. 2021 Jan;53(1):259-268. (PMID: 32662130)
AJNR Am J Neuroradiol. 2007 Nov-Dec;28(10):1949-55. (PMID: 17898200)
Stroke. 2003 Jan;34(1):16-21. (PMID: 12511744)
Radiology. 2019 Jan;290(1):187-194. (PMID: 30351253)
Radiology. 2017 Aug;284(2):574-582. (PMID: 28436741)
Int J Comput Assist Radiol Surg. 2020 Apr;15(4):715-723. (PMID: 32056126)
Stroke. 2013 Sep;44(9):2414-21. (PMID: 23868274)
J Neuroradiol. 2007 Oct;34(4):243-9. (PMID: 17761283)
Med Image Anal. 2017 Feb;36:61-78. (PMID: 27865153)
Stroke. 2013 Jan;44(1):29-37. (PMID: 23238862)
Radiology. 2009 Sep;252(3):808-15. (PMID: 19508992)
Lancet. 2007 Jan 27;369(9558):306-18. (PMID: 17258671)
Insights Imaging. 2017 Feb;8(1):171-182. (PMID: 27928712)
JAMA Netw Open. 2019 Jun 5;2(6):e195600. (PMID: 31173130)
Lancet. 2002 Oct 26;360(9342):1267-74. (PMID: 12414200)
Radiographics. 2015 Oct;35(6):1668-76. (PMID: 26466178)
AJNR Am J Neuroradiol. 2021 Apr;42(4):655-662. (PMID: 33541907)
Radiology. 2004 Feb;230(2):510-8. (PMID: 14699177)
Neuroimage. 2005 Jul 1;26(3):839-51. (PMID: 15955494)
Radiology. 2018 Apr;287(1):313-322. (PMID: 29095675)
Radiology. 2021 Jan;298(1):155-163. (PMID: 33141003)
Biometrics. 1977 Mar;33(1):159-74. (PMID: 843571)
Nat Commun. 2020 Nov 30;11(1):6090. (PMID: 33257700)
Lancet Oncol. 2019 May;20(5):728-740. (PMID: 30952559)
Contributed Indexing:
Keywords: Aneurysmal subarachnoid hemorrhage; Aneurysms; CT angiography; Convolutional neural networks; Deep learning
Entry Date(s):
Date Created: 20210410 Date Completed: 20211116 Latest Revision: 20220218
Update Code:
20240105
PubMed Central ID:
PMC8589782
DOI:
10.1007/s00234-021-02697-9
PMID:
33837806
Czasopismo naukowe
Purpose: 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).
Methods: 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 3 , 13.0% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared.
Results: 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).
Conclusion: 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.
(© 2021. The Author(s).)

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies